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

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

Neuron 854 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.6186. Min Act: -0.1700

Data Index: 798909 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.5872. Min Act: -0.1700

Data Index: 147396 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.6186. Min Act: -0.1700

Data Index: 448243 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.5872. Min Act: -0.1700

Data Index: 715430 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.5559. Min Act: -0.1700

Data Index: 489422 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.5559. Min Act: -0.1700

Data Index: 639735 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.5246. Min Act: -0.1700

Data Index: 1324875 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4933. Min Act: -0.1700

Data Index: 955845 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4619. Min Act: -0.1700

Data Index: 1333410 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4306. Min Act: -0.1700

Data Index: 227166 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4306. Min Act: -0.1700

Data Index: 947212 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4306. Min Act: -0.1700

Data Index: 1084144 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4306. Min Act: -0.1700

Data Index: 1132309 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4619. Min Act: -0.1700

Data Index: 1282688 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3992. Min Act: -0.1700

Data Index: 876019 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3992. Min Act: -0.1700

Data Index: 748596 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4306. Min Act: -0.1700

Data Index: 662442 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3992. Min Act: -0.1700

Data Index: 1277218 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3992. Min Act: -0.1700

Data Index: 184116 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3678. Min Act: -0.1700

Data Index: 293065 (C4 (Web Text))

Max Activating Token Index: 353