Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 837 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.6179. Min Act: -0.1700

Data Index: 1075218 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.6336. Min Act: -0.1700

Data Index: 919523 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.6023. Min Act: -0.1700

Data Index: 335979 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5396. Min Act: -0.1700

Data Index: 504120 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5866. Min Act: -0.1700

Data Index: 1006962 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.6179. Min Act: -0.1700

Data Index: 847371 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.6023. Min Act: -0.1700

Data Index: 315215 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5553. Min Act: -0.1700

Data Index: 1138118 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5553. Min Act: -0.1700

Data Index: 271836 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5553. Min Act: -0.1700

Data Index: 1198236 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5396. Min Act: -0.1700

Data Index: 1280335 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5553. Min Act: -0.1700

Data Index: 1203164 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5083. Min Act: -0.1700

Data Index: 144974 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5709. Min Act: -0.1700

Data Index: 57987 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5240. Min Act: -0.1700

Data Index: 585192 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.4926. Min Act: -0.1700

Data Index: 1029179 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.5240. Min Act: -0.1700

Data Index: 19923 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.4926. Min Act: -0.1700

Data Index: 1073972 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.4770. Min Act: -0.1700

Data Index: 913546 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 3.6336. Min Range: -3.6336

Max Act: 3.4770. Min Act: -0.1700

Data Index: 77574 (C4 (Web Text))

Max Activating Token Index: 195