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

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

Neuron 797 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: 3.6294. Min Range: -3.6294

Max Act: 3.6294. Min Act: -0.1700

Data Index: 802259 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.6294. Min Act: -0.1700

Data Index: 387298 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5981. Min Act: -0.1700

Data Index: 37640 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5981. Min Act: -0.1700

Data Index: 103143 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5668. Min Act: -0.1700

Data Index: 400484 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5511. Min Act: -0.1700

Data Index: 509771 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5511. Min Act: -0.1700

Data Index: 659487 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5198. Min Act: -0.1700

Data Index: 443515 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5198. Min Act: -0.1700

Data Index: 808995 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5511. Min Act: -0.1700

Data Index: 1151650 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5511. Min Act: -0.1700

Data Index: 1102289 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5355. Min Act: -0.1700

Data Index: 1203374 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5198. Min Act: -0.1700

Data Index: 1350569 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5041. Min Act: -0.1700

Data Index: 1311055 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5355. Min Act: -0.1700

Data Index: 227247 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5198. Min Act: -0.1700

Data Index: 555804 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5198. Min Act: -0.1700

Data Index: 32348 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.4884. Min Act: -0.1700

Data Index: 152362 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5198. Min Act: -0.1700

Data Index: 777097 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 3.6294. Min Range: -3.6294

Max Act: 3.5198. Min Act: -0.1700

Data Index: 211618 (C4 (Web Text))

Max Activating Token Index: 133