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

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

Neuron 1062 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: 0.1563. Min Range: -0.1563

Max Act: 0.1563. Min Act: -0.0002

Data Index: 1120338 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1476. Min Act: -0.0002

Data Index: 478017 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1153209 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1440. Min Act: -0.0002

Data Index: 1023160 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1453. Min Act: -0.0002

Data Index: 1067899 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1298. Min Act: -0.0001

Data Index: 287686 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1435. Min Act: -0.0001

Data Index: 108741 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1390. Min Act: -0.0002

Data Index: 673065 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1062422 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1371. Min Act: -0.0002

Data Index: 1299431 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1306. Min Act: -0.0002

Data Index: 685927 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1292. Min Act: -0.0001

Data Index: 332495 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1299. Min Act: -0.0002

Data Index: 48436 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1252. Min Act: -0.0002

Data Index: 823138 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1258. Min Act: -0.0002

Data Index: 187560 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1244. Min Act: -0.0002

Data Index: 149891 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1165. Min Act: -0.0001

Data Index: 353385 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1200. Min Act: -0.0002

Data Index: 1346864 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1226. Min Act: -0.0002

Data Index: 1226584 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1276247 (C4 (Web Text))

Max Activating Token Index: 597