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

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

Neuron 816 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2412. Min Act: -0.0003

Data Index: 1146550 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2390. Min Act: -0.0003

Data Index: 622284 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2548. Min Act: -0.0003

Data Index: 908391 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2455. Min Act: -0.0003

Data Index: 1145281 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2448. Min Act: -0.0003

Data Index: 532244 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2383. Min Act: -0.0002

Data Index: 129061 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2375. Min Act: -0.0003

Data Index: 1344512 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2351. Min Act: -0.0003

Data Index: 43871 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2327. Min Act: -0.0003

Data Index: 1283362 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2431. Min Act: -0.0003

Data Index: 127720 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2330. Min Act: -0.0003

Data Index: 1334709 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2235. Min Act: -0.0003

Data Index: 1007171 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2388. Min Act: -0.0003

Data Index: 305689 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2291. Min Act: -0.0002

Data Index: 958088 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2285. Min Act: -0.0003

Data Index: 797811 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2283. Min Act: -0.0003

Data Index: 1346889 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2264. Min Act: -0.0003

Data Index: 278160 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2251. Min Act: -0.0003

Data Index: 1059005 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2345. Min Act: -0.0003

Data Index: 328587 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2344. Min Act: -0.0003

Data Index: 229087 (C4 (Web Text))

Max Activating Token Index: 144