< Prev | Home | Model | Random | Next >

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

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

Neuron 1186 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: 6.9158. Min Range: -6.9158

Max Act: 6.9158. Min Act: -0.1700

Data Index: 586399 (C4 (Web Text))

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.5721. Min Act: -0.1700

Data Index: 1516247 (Python Code)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.5408. Min Act: -0.1700

Data Index: 101572 (C4 (Web Text))

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.5096. Min Act: -0.1700

Data Index: 633459 (C4 (Web Text))

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.4471. Min Act: -0.1700

Data Index: 683876 (C4 (Web Text))

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.4783. Min Act: -0.1700

Data Index: 845118 (C4 (Web Text))

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.3846. Min Act: -0.1700

Data Index: 1158065 (C4 (Web Text))

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.1658. Min Act: -0.1700

Data Index: 904016 (C4 (Web Text))

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.2283. Min Act: -0.1700

Data Index: 932462 (C4 (Web Text))

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.2283. Min Act: -0.1700

Data Index: 421493 (C4 (Web Text))

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.1346. Min Act: -0.1700

Data Index: 1582667 (Python Code)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.1971. Min Act: -0.1700

Data Index: 1164804 (C4 (Web Text))

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.1033. Min Act: -0.1700

Data Index: 134184 (C4 (Web Text))

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.0721. Min Act: -0.1700

Data Index: 626490 (C4 (Web Text))

Max Activating Token Index: 622

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.0096. Min Act: -0.1700

Data Index: 1098462 (C4 (Web Text))

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.0408. Min Act: -0.1700

Data Index: 786767 (C4 (Web Text))

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.0408. Min Act: -0.1700

Data Index: 391698 (C4 (Web Text))

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.0096. Min Act: -0.1700

Data Index: 34968 (C4 (Web Text))

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.0096. Min Act: -0.1700

Data Index: 1345596 (C4 (Web Text))

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.9158. Min Range: -6.9158

Max Act: 6.0408. Min Act: -0.1700

Data Index: 474648 (C4 (Web Text))

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #19