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

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

Neuron 845 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.8447. Min Act: -0.1700

Data Index: 1322725 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.7508. Min Act: -0.1700

Data Index: 378638 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.8447. Min Act: -0.1700

Data Index: 1034509 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.7508. Min Act: -0.1700

Data Index: 927033 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.6570. Min Act: -0.1700

Data Index: 491265 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.7196. Min Act: -0.1700

Data Index: 185896 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.6883. Min Act: -0.1700

Data Index: 1292405 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.6883. Min Act: -0.1700

Data Index: 1317584 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.6257. Min Act: -0.1700

Data Index: 929290 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.7508. Min Act: -0.1700

Data Index: 75030 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.6257. Min Act: -0.1700

Data Index: 322009 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.6257. Min Act: -0.1700

Data Index: 58036 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.5630. Min Act: -0.1700

Data Index: 1163281 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.4063. Min Act: -0.1700

Data Index: 261721 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.5630. Min Act: -0.1700

Data Index: 894243 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.4690. Min Act: -0.1700

Data Index: 608467 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.4377. Min Act: -0.1700

Data Index: 18391 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.3749. Min Act: -0.1700

Data Index: 742262 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.3122. Min Act: -0.1700

Data Index: 256890 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 3.8447. Min Range: -3.8447

Max Act: 3.3122. Min Act: -0.1700

Data Index: 221031 (C4 (Web Text))

Max Activating Token Index: 516