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

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

Neuron 1195 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1102155 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1176449 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1335481 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0428. Min Act: -0.0002

Data Index: 241770 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0428. Min Act: -0.0002

Data Index: 67069 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1099094 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0420. Min Act: -0.0002

Data Index: 473063 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0414. Min Act: -0.0002

Data Index: 157894 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0390. Min Act: -0.0002

Data Index: 49152 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0397. Min Act: -0.0002

Data Index: 737578 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0393. Min Act: -0.0002

Data Index: 304999 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0390. Min Act: -0.0002

Data Index: 203968 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0390. Min Act: -0.0002

Data Index: 10032 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0386. Min Act: -0.0002

Data Index: 295753 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0401. Min Act: -0.0002

Data Index: 146174 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1332212 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1155585 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0383. Min Act: -0.0002

Data Index: 489684 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0383. Min Act: -0.0002

Data Index: 493894 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0395. Min Act: -0.0002

Data Index: 11214 (C4 (Web Text))

Max Activating Token Index: 656