Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2230 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.3288. Min Act: -0.0000

Data Index: 551428 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2557. Min Act: -0.0000

Data Index: 316198 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2628. Min Act: -0.0000

Data Index: 183073 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2471. Min Act: -0.0001

Data Index: 1166660 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2502. Min Act: -0.0000

Data Index: 605509 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2439. Min Act: -0.0000

Data Index: 521165 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2416. Min Act: -0.0000

Data Index: 917547 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1338050 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2379. Min Act: -0.0000

Data Index: 146620 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2426. Min Act: -0.0000

Data Index: 782866 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2273. Min Act: -0.0000

Data Index: 716596 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2283. Min Act: -0.0000

Data Index: 619067 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2339. Min Act: -0.0000

Data Index: 752623 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2236. Min Act: -0.0000

Data Index: 821252 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2245. Min Act: -0.0000

Data Index: 889258 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2275. Min Act: -0.0001

Data Index: 169763 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2273. Min Act: -0.0000

Data Index: 770939 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2236. Min Act: -0.0001

Data Index: 80425 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2109. Min Act: -0.0000

Data Index: 868220 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.3288. Min Range: -0.3288

Max Act: 0.2096. Min Act: -0.0000

Data Index: 880067 (C4 (Web Text))

Max Activating Token Index: 985