< Prev | Home | Model | Random | Next >

Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 467 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!



Text #0

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.6593. Min Act: -0.1700

Data Index: 1407521 (Python Code)

Max Activating Token Index: 953

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.6429. Min Act: -0.1700

Data Index: 1543939 (Python Code)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.6247. Min Act: -0.1700

Data Index: 1621545 (Python Code)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5799. Min Act: -0.1700

Data Index: 1548553 (Python Code)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5569. Min Act: -0.1700

Data Index: 1454569 (Python Code)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5318. Min Act: -0.1700

Data Index: 1368105 (Python Code)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5434. Min Act: -0.1700

Data Index: 1496376 (Python Code)

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5431. Min Act: -0.1700

Data Index: 1567048 (Python Code)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5208. Min Act: -0.1700

Data Index: 1552740 (Python Code)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5154. Min Act: -0.1700

Data Index: 1485706 (Python Code)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5161. Min Act: -0.1700

Data Index: 1511409 (Python Code)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5031. Min Act: -0.1700

Data Index: 1379713 (Python Code)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5047. Min Act: -0.1700

Data Index: 1372708 (Python Code)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.5062. Min Act: -0.1700

Data Index: 1481877 (Python Code)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.4776. Min Act: -0.1700

Data Index: 1409613 (Python Code)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.4938. Min Act: -0.1700

Data Index: 1638164 (Python Code)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.4741. Min Act: -0.1700

Data Index: 1488925 (Python Code)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.4815. Min Act: -0.1700

Data Index: 1441547 (Python Code)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.4675. Min Act: -0.1700

Data Index: 1554260 (Python Code)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6593. Min Range: -2.6593

Max Act: 2.4770. Min Act: -0.1700

Data Index: 1548231 (Python Code)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #19