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

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

Neuron 1635 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: 0.1351. Min Range: -0.1351

Max Act: 0.1261. Min Act: -0.0001

Data Index: 484043 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1351. Min Act: -0.0001

Data Index: 182399 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1277. Min Act: -0.0002

Data Index: 315283 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1267. Min Act: -0.0002

Data Index: 818342 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1159. Min Act: -0.0002

Data Index: 732423 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1161. Min Act: -0.0002

Data Index: 1042675 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1213. Min Act: -0.0002

Data Index: 795107 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1012222 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1027. Min Act: -0.0002

Data Index: 847058 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0960. Min Act: -0.0001

Data Index: 340811 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1070764 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1103. Min Act: -0.0002

Data Index: 513314 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1081. Min Act: -0.0001

Data Index: 343735 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1083. Min Act: -0.0002

Data Index: 996220 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1069. Min Act: -0.0002

Data Index: 294047 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1291972 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1163. Min Act: -0.0002

Data Index: 593807 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1315342 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1035. Min Act: -0.0001

Data Index: 194295 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1169045 (C4 (Web Text))

Max Activating Token Index: 72