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

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

Neuron 1520 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.5988. Min Act: -0.1700

Data Index: 1295267 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.5204. Min Act: -0.1700

Data Index: 1039794 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4578. Min Act: -0.1700

Data Index: 54684 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4421. Min Act: -0.1700

Data Index: 955458 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4107. Min Act: -0.1700

Data Index: 1015689 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4107. Min Act: -0.1700

Data Index: 596044 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3950. Min Act: -0.1700

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3794. Min Act: -0.1700

Data Index: 403530 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3950. Min Act: -0.1700

Data Index: 651226 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3794. Min Act: -0.1700

Data Index: 163434 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3637. Min Act: -0.1700

Data Index: 1001497 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3480. Min Act: -0.1700

Data Index: 761648 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3794. Min Act: -0.1700

Data Index: 656142 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3323. Min Act: -0.1700

Data Index: 1013922 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3637. Min Act: -0.1700

Data Index: 1178588 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3480. Min Act: -0.1700

Data Index: 650170 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3637. Min Act: -0.1700

Data Index: 518483 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3480. Min Act: -0.1700

Data Index: 114666 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3323. Min Act: -0.1700

Data Index: 1352680 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3323. Min Act: -0.1700

Data Index: 362240 (C4 (Web Text))

Max Activating Token Index: 412