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

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

Neuron 961 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 592281 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0361. Min Act: -0.0002

Data Index: 584917 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0354. Min Act: -0.0002

Data Index: 680301 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0325. Min Act: -0.0001

Data Index: 796419 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0317. Min Act: -0.0002

Data Index: 712269 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1547535 (Python Code)

Max Activating Token Index: 574

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0312. Min Act: -0.0001

Data Index: 185366 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1088788 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1149467 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1599840 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0262. Min Act: -0.0002

Data Index: 807569 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1001342 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0283. Min Act: -0.0001

Data Index: 344195 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0284. Min Act: -0.0001

Data Index: 811831 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0297. Min Act: -0.0001

Data Index: 612003 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1357705 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0278. Min Act: -0.0001

Data Index: 489657 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0278. Min Act: -0.0001

Data Index: 357118 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0272. Min Act: -0.0001

Data Index: 615964 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1480174 (Python Code)

Max Activating Token Index: 750