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

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

Neuron 760 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: 7.9419. Min Range: -7.9419

Max Act: 7.9419. Min Act: -0.1699

Data Index: 730002 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.8482. Min Act: -0.1700

Data Index: 83037 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.5357. Min Act: -0.1700

Data Index: 737286 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.5669. Min Act: -0.1700

Data Index: 462202 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.5044. Min Act: -0.1696

Data Index: 1172850 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.4107. Min Act: -0.1700

Data Index: 372966 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.4107. Min Act: -0.1700

Data Index: 193364 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.3794. Min Act: -0.1700

Data Index: 58559 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.4419. Min Act: -0.1700

Data Index: 264524 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.3794. Min Act: -0.1700

Data Index: 577987 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.2544. Min Act: -0.1700

Data Index: 791224 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.3169. Min Act: -0.1700

Data Index: 803075 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.3169. Min Act: -0.1700

Data Index: 946049 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.1919. Min Act: -0.1700

Data Index: 538050 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.4419. Min Act: -0.1698

Data Index: 108799 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.1919. Min Act: -0.1700

Data Index: 857352 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.1294. Min Act: -0.1700

Data Index: 771913 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.2544. Min Act: -0.1700

Data Index: 1157049 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.1919. Min Act: -0.1700

Data Index: 973210 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 7.9419. Min Range: -7.9419

Max Act: 7.2232. Min Act: -0.1700

Data Index: 982855 (C4 (Web Text))

Max Activating Token Index: 445