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

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

Neuron 2676 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1311. Min Act: -0.0001

Data Index: 756883 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1156. Min Act: -0.0001

Data Index: 73192 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1204. Min Act: -0.0001

Data Index: 683105 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1184. Min Act: -0.0001

Data Index: 383840 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1258. Min Act: -0.0001

Data Index: 715594 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1197. Min Act: -0.0001

Data Index: 273349 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1212442 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1002. Min Act: -0.0001

Data Index: 218660 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1117. Min Act: -0.0001

Data Index: 227782 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1115. Min Act: -0.0001

Data Index: 41753 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1060. Min Act: -0.0001

Data Index: 815002 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1141. Min Act: -0.0001

Data Index: 528889 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1112. Min Act: -0.0001

Data Index: 363735 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1150. Min Act: -0.0001

Data Index: 204703 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1065. Min Act: -0.0001

Data Index: 800795 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1056. Min Act: -0.0001

Data Index: 158809 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1128. Min Act: -0.0001

Data Index: 696536 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0999. Min Act: -0.0001

Data Index: 724939 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1079. Min Act: -0.0001

Data Index: 999491 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1105. Min Act: -0.0001

Data Index: 891811 (C4 (Web Text))

Max Activating Token Index: 417