< Prev | Home | Model | Random | Next >

Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 988 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')



Text #0

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.6437. Min Act: -0.1700

Data Index: 1367224 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.5955. Min Act: -0.1618

Data Index: 1649409 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.4499. Min Act: -0.1700

Data Index: 1383563 (Python Code)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.4174. Min Act: -0.1700

Data Index: 1561782 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.4174. Min Act: -0.1700

Data Index: 847704 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.4011. Min Act: -0.1700

Data Index: 1643805 (Python Code)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.4011. Min Act: -0.1681

Data Index: 1446813 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.4011. Min Act: -0.1699

Data Index: 1428317 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3847. Min Act: -0.1700

Data Index: 1573985 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3684. Min Act: -0.1700

Data Index: 1575827 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3684. Min Act: -0.1700

Data Index: 1389398 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3684. Min Act: -0.1700

Data Index: 1618800 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3684. Min Act: -0.1700

Data Index: 1510667 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3684. Min Act: -0.1700

Data Index: 1587717 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3357. Min Act: -0.1700

Data Index: 1479167 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3357. Min Act: -0.1700

Data Index: 1495115 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3193. Min Act: -0.1700

Data Index: 1389786 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3357. Min Act: -0.1700

Data Index: 1377197 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3357. Min Act: -0.1700

Data Index: 1582711 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.3357. Min Act: -0.1700

Data Index: 429921 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #19