< Prev | Home | Model | Random | Next >

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

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

Neuron 1685 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: 6.1418. Min Range: -6.1418

Max Act: 6.1106. Min Act: -0.1700

Data Index: 307282 (C4 (Web Text))

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.1418. Min Range: -6.1418

Max Act: 6.0793. Min Act: -0.1700

Data Index: 930649 (C4 (Web Text))

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.1418. Min Range: -6.1418

Max Act: 6.1418. Min Act: -0.1700

Data Index: 762894 (C4 (Web Text))

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.9543. Min Act: -0.1700

Data Index: 944811 (C4 (Web Text))

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.9543. Min Act: -0.1700

Data Index: 418542 (C4 (Web Text))

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.9231. Min Act: -0.1700

Data Index: 1429449 (Python Code)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.7981. Min Act: -0.1700

Data Index: 25288 (C4 (Web Text))

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.9231. Min Act: -0.1700

Data Index: 937138 (C4 (Web Text))

Max Activating Token Index: 409

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.9543. Min Act: -0.1700

Data Index: 251974 (C4 (Web Text))

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.9231. Min Act: -0.1700

Data Index: 600362 (C4 (Web Text))

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.9231. Min Act: -0.1700

Data Index: 206911 (C4 (Web Text))

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.9543. Min Act: -0.1700

Data Index: 384144 (C4 (Web Text))

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.8606. Min Act: -0.1700

Data Index: 48862 (C4 (Web Text))

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.8918. Min Act: -0.1700

Data Index: 1276423 (C4 (Web Text))

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.9231. Min Act: -0.1700

Data Index: 575597 (C4 (Web Text))

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.8606. Min Act: -0.1700

Data Index: 187773 (C4 (Web Text))

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.8918. Min Act: -0.1700

Data Index: 35982 (C4 (Web Text))

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.7981. Min Act: -0.1700

Data Index: 1193912 (C4 (Web Text))

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.8293. Min Act: -0.1700

Data Index: 254480 (C4 (Web Text))

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.1418. Min Range: -6.1418

Max Act: 5.8918. Min Act: -0.1700

Data Index: 1364537 (Python Code)

Max Activating Token Index: 51

Click toggle to see full text

Truncated

Full Text #19