Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4083 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2691. Min Act: -0.0001

Data Index: 796507 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1237744 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2640. Min Act: -0.0001

Data Index: 791947 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2584. Min Act: -0.0001

Data Index: 831088 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2294. Min Act: -0.0001

Data Index: 16090 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2174. Min Act: -0.0001

Data Index: 316300 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2360. Min Act: -0.0001

Data Index: 922234 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2298. Min Act: -0.0001

Data Index: 426748 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1185007 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2278. Min Act: -0.0001

Data Index: 1077596 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2325. Min Act: -0.0001

Data Index: 833701 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2316. Min Act: -0.0001

Data Index: 423860 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2384. Min Act: -0.0001

Data Index: 70192 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2269. Min Act: -0.0001

Data Index: 387734 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2257. Min Act: -0.0001

Data Index: 586770 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2309. Min Act: -0.0001

Data Index: 826176 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2231. Min Act: -0.0001

Data Index: 1082012 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2400. Min Act: -0.0001

Data Index: 1229368 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2314. Min Act: -0.0001

Data Index: 748499 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2207. Min Act: -0.0001

Data Index: 329067 (C4 (Web Text))

Max Activating Token Index: 32