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

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

Neuron 1848 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3541. Min Act: -0.0000

Data Index: 126559 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3336. Min Act: 0.0001

Data Index: 100398 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3314. Min Act: -0.0000

Data Index: 436428 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3395. Min Act: 0.0000

Data Index: 97271 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3485. Min Act: -0.0000

Data Index: 326940 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3232. Min Act: -0.0000

Data Index: 577482 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3209. Min Act: -0.0000

Data Index: 746652 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3157. Min Act: -0.0000

Data Index: 651041 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3168. Min Act: 0.0000

Data Index: 942910 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3267. Min Act: -0.0000

Data Index: 169054 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3179. Min Act: -0.0000

Data Index: 526845 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3130. Min Act: -0.0000

Data Index: 56604 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1168777 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1159244 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2981. Min Act: 0.0000

Data Index: 23041 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2833. Min Act: -0.0000

Data Index: 208124 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3108. Min Act: -0.0000

Data Index: 585750 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2844. Min Act: -0.0000

Data Index: 887299 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2924. Min Act: -0.0000

Data Index: 987287 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2875. Min Act: -0.0000

Data Index: 844167 (C4 (Web Text))

Max Activating Token Index: 240