Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 176 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0005

Data Index: 926314 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0385. Min Act: -0.0005

Data Index: 829619 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0390. Min Act: -0.0005

Data Index: 719072 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0394. Min Act: -0.0005

Data Index: 521711 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0358. Min Act: -0.0005

Data Index: 442292 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0335. Min Act: -0.0005

Data Index: 647018 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0369. Min Act: -0.0005

Data Index: 411359 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0363. Min Act: -0.0005

Data Index: 1302923 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0347. Min Act: -0.0004

Data Index: 229462 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0338. Min Act: -0.0005

Data Index: 992564 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0367. Min Act: -0.0005

Data Index: 15718 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0360. Min Act: -0.0005

Data Index: 306842 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0356. Min Act: -0.0005

Data Index: 1188178 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0347. Min Act: -0.0005

Data Index: 347305 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0341. Min Act: -0.0005

Data Index: 403153 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0353. Min Act: -0.0005

Data Index: 1052904 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0326. Min Act: -0.0005

Data Index: 370855 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0334. Min Act: -0.0005

Data Index: 134069 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0352. Min Act: -0.0005

Data Index: 1165936 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0345. Min Act: -0.0005

Data Index: 1649062 (Python Code)

Max Activating Token Index: 86