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

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

Neuron 1675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2233. Min Act: -0.0000

Data Index: 797701 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1800. Min Act: -0.0000

Data Index: 438108 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1686. Min Act: -0.0000

Data Index: 71778 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1678. Min Act: -0.0000

Data Index: 93515 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1539. Min Act: -0.0000

Data Index: 974257 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1580. Min Act: -0.0000

Data Index: 517072 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1085804 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1039117 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1432. Min Act: -0.0000

Data Index: 318271 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1360. Min Act: -0.0000

Data Index: 26727 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1233837 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1228. Min Act: -0.0000

Data Index: 693847 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1244. Min Act: -0.0000

Data Index: 932790 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1308. Min Act: -0.0000

Data Index: 534817 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1313. Min Act: -0.0000

Data Index: 671530 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1225. Min Act: -0.0000

Data Index: 607879 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1164. Min Act: -0.0000

Data Index: 916791 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1215. Min Act: -0.0000

Data Index: 886199 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.0997. Min Act: -0.0000

Data Index: 657097 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1071. Min Act: -0.0000

Data Index: 778502 (C4 (Web Text))

Max Activating Token Index: 931