Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3448 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1813. Min Act: -0.0000

Data Index: 894427 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1387. Min Act: -0.0000

Data Index: 556932 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1368. Min Act: -0.0001

Data Index: 498707 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1395. Min Act: -0.0000

Data Index: 177571 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1299. Min Act: -0.0000

Data Index: 49286 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1294. Min Act: -0.0000

Data Index: 196236 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1233. Min Act: -0.0000

Data Index: 271495 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1175. Min Act: -0.0000

Data Index: 198791 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1247. Min Act: -0.0000

Data Index: 876706 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1192. Min Act: -0.0000

Data Index: 662648 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1149. Min Act: -0.0000

Data Index: 142639 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1175. Min Act: -0.0001

Data Index: 223931 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1291439 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1106. Min Act: -0.0000

Data Index: 364173 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1154. Min Act: -0.0000

Data Index: 168021 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1095. Min Act: -0.0000

Data Index: 760559 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1293 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1114. Min Act: -0.0000

Data Index: 552644 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1059244 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1074. Min Act: -0.0001

Data Index: 302854 (C4 (Web Text))

Max Activating Token Index: 166