Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3224 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.7195. Min Range: -6.7195

Max Act: 6.6323. Min Act: -0.0000

Data Index: 658962 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 6.7195. Min Range: -6.7195

Max Act: 6.5636. Min Act: -0.0000

Data Index: 927834 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 6.7195. Min Range: -6.7195

Max Act: 6.7195. Min Act: -0.0000

Data Index: 534124 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.9682. Min Act: -0.0000

Data Index: 375000 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 6.7195. Min Range: -6.7195

Max Act: 6.1163. Min Act: -0.0000

Data Index: 145259 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.7234. Min Act: -0.0000

Data Index: 664181 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.8182. Min Act: -0.0000

Data Index: 661814 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.5918. Min Act: -0.0000

Data Index: 315878 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.2803. Min Act: -0.0000

Data Index: 85215 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.4539. Min Act: -0.0000

Data Index: 1357261 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.6150. Min Act: -0.0000

Data Index: 684490 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.4112. Min Act: -0.0000

Data Index: 594760 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.3858. Min Act: -0.0000

Data Index: 632559 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.1335. Min Act: -0.0000

Data Index: 80718 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.3009. Min Act: -0.0000

Data Index: 652219 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.0805. Min Act: -0.0000

Data Index: 1291781 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.4518. Min Act: -0.0000

Data Index: 30224 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.0407. Min Act: -0.0000

Data Index: 220236 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.0779. Min Act: -0.0000

Data Index: 195205 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 6.7195. Min Range: -6.7195

Max Act: 5.2466. Min Act: -0.0000

Data Index: 1215821 (C4 (Web Text))

Max Activating Token Index: 571