< Prev | Home | Model | Random | Next >

Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1450 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')



Text #0

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.6441. Min Act: -0.1700

Data Index: 1440570 (Python Code)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.5190. Min Act: -0.1700

Data Index: 1253926 (C4 (Web Text))

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.4722. Min Act: -0.1700

Data Index: 1429560 (Python Code)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.3628. Min Act: -0.1700

Data Index: 1580009 (Python Code)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.3315. Min Act: -0.1700

Data Index: 1571365 (Python Code)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.2534. Min Act: -0.1700

Data Index: 1444100 (Python Code)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.2534. Min Act: -0.1700

Data Index: 1404621 (Python Code)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.2065. Min Act: -0.1700

Data Index: 1428350 (Python Code)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.1284. Min Act: -0.1700

Data Index: 1463615 (Python Code)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.1284. Min Act: -0.1700

Data Index: 1197326 (C4 (Web Text))

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.1596. Min Act: -0.1700

Data Index: 1447536 (Python Code)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.1284. Min Act: -0.1700

Data Index: 1509869 (Python Code)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.0971. Min Act: -0.1700

Data Index: 1394657 (Python Code)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.0502. Min Act: -0.1700

Data Index: 1415091 (Python Code)

Max Activating Token Index: 60

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.0658. Min Act: -0.1700

Data Index: 1586793 (Python Code)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.0971. Min Act: -0.1700

Data Index: 1421334 (Python Code)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.0815. Min Act: -0.1700

Data Index: 1481526 (Python Code)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.0658. Min Act: -0.1700

Data Index: 1361418 (Python Code)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.0658. Min Act: -0.1700

Data Index: 1604371 (Python Code)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.6441. Min Range: -4.6441

Max Act: 4.1127. Min Act: -0.1700

Data Index: 1558081 (Python Code)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #19