Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5950 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1885. Min Act: -0.0000

Data Index: 32325 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1698. Min Act: -0.0000

Data Index: 896169 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1754. Min Act: -0.0000

Data Index: 440027 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1585. Min Act: -0.0000

Data Index: 875212 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1208029 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1512. Min Act: -0.0000

Data Index: 103095 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1528. Min Act: -0.0000

Data Index: 971830 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1446. Min Act: -0.0000

Data Index: 614548 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1400. Min Act: -0.0000

Data Index: 10361 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1182970 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1377. Min Act: -0.0000

Data Index: 124648 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1287098 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1171. Min Act: -0.0000

Data Index: 633461 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1077997 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1258. Min Act: -0.0000

Data Index: 401784 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1137440 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1236. Min Act: -0.0000

Data Index: 291468 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1121162 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1305653 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1225. Min Act: -0.0000

Data Index: 920656 (C4 (Web Text))

Max Activating Token Index: 171