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

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

Neuron 5612 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.4177. Min Act: -0.0000

Data Index: 943490 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3999. Min Act: -0.0000

Data Index: 904969 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3677. Min Act: -0.0000

Data Index: 456859 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3723. Min Act: -0.0000

Data Index: 38111 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3656. Min Act: 0.0000

Data Index: 963071 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3549. Min Act: -0.0000

Data Index: 962659 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3449. Min Act: -0.0000

Data Index: 217789 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3331. Min Act: -0.0000

Data Index: 457026 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3241. Min Act: -0.0000

Data Index: 989757 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3335. Min Act: -0.0000

Data Index: 577942 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3313. Min Act: -0.0000

Data Index: 183040 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3358. Min Act: -0.0000

Data Index: 384548 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3199. Min Act: -0.0000

Data Index: 86612 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3158. Min Act: -0.0000

Data Index: 831770 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3204. Min Act: -0.0000

Data Index: 236303 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.2976. Min Act: -0.0000

Data Index: 240096 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3312. Min Act: -0.0000

Data Index: 938571 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3079. Min Act: -0.0000

Data Index: 529689 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.2920. Min Act: -0.0000

Data Index: 897958 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.2837. Min Act: -0.0000

Data Index: 997595 (C4 (Web Text))

Max Activating Token Index: 459