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

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

Neuron 5692 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1286327 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1145381 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1109982 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1611. Min Act: -0.0001

Data Index: 816391 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1384. Min Act: -0.0001

Data Index: 565792 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1419. Min Act: -0.0001

Data Index: 969123 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1063863 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1264. Min Act: -0.0001

Data Index: 339457 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1269. Min Act: -0.0001

Data Index: 551670 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1249042 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1210. Min Act: -0.0001

Data Index: 422985 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1198. Min Act: -0.0001

Data Index: 464510 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1020821 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1015482 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1205. Min Act: -0.0001

Data Index: 995754 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1175. Min Act: -0.0001

Data Index: 497702 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1074. Min Act: -0.0001

Data Index: 353706 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1060. Min Act: -0.0001

Data Index: 638922 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1131. Min Act: -0.0001

Data Index: 845636 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1092. Min Act: -0.0001

Data Index: 90292 (C4 (Web Text))

Max Activating Token Index: 69