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

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

Neuron 1754 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: 0.3372. Min Range: -0.3372

Max Act: 0.3372. Min Act: -0.0000

Data Index: 528684 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3116. Min Act: -0.0000

Data Index: 704014 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3085. Min Act: -0.0000

Data Index: 152251 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2967. Min Act: -0.0000

Data Index: 219596 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1222034 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2579. Min Act: -0.0001

Data Index: 1104383 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1022004 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2388. Min Act: -0.0001

Data Index: 301168 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2280. Min Act: -0.0000

Data Index: 475356 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2257. Min Act: 0.0001

Data Index: 885652 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2329. Min Act: -0.0000

Data Index: 710065 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2309. Min Act: -0.0000

Data Index: 459962 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1171137 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2324. Min Act: -0.0000

Data Index: 229762 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2313. Min Act: -0.0000

Data Index: 107037 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1042222 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1096328 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2308. Min Act: -0.0000

Data Index: 411386 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1271422 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1157727 (C4 (Web Text))

Max Activating Token Index: 111