Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 774 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0003

Data Index: 700274 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0363. Min Act: -0.0003

Data Index: 32274 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1144881 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0348. Min Act: -0.0002

Data Index: 60973 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0341. Min Act: -0.0003

Data Index: 28367 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0332. Min Act: -0.0003

Data Index: 702156 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0330. Min Act: -0.0003

Data Index: 78963 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0329. Min Act: -0.0003

Data Index: 965409 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0334. Min Act: -0.0003

Data Index: 853328 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1189317 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0330. Min Act: -0.0004

Data Index: 160786 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0329. Min Act: -0.0003

Data Index: 670931 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0328. Min Act: -0.0003

Data Index: 506267 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0325. Min Act: -0.0003

Data Index: 97923 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0322. Min Act: -0.0003

Data Index: 644675 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0312. Min Act: -0.0003

Data Index: 451638 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0315. Min Act: -0.0003

Data Index: 464577 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0314. Min Act: -0.0003

Data Index: 757954 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0310. Min Act: -0.0003

Data Index: 528037 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0308. Min Act: -0.0004

Data Index: 831546 (C4 (Web Text))

Max Activating Token Index: 802