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

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

Neuron 1401 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1226. Min Act: -0.0002

Data Index: 445193 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1207. Min Act: -0.0001

Data Index: 120889 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1186. Min Act: -0.0002

Data Index: 296743 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1013348 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0981. Min Act: -0.0002

Data Index: 1059266 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0964. Min Act: -0.0002

Data Index: 550439 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0902. Min Act: -0.0001

Data Index: 494303 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1012. Min Act: -0.0002

Data Index: 841989 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1034. Min Act: -0.0002

Data Index: 78004 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1009. Min Act: -0.0002

Data Index: 35392 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0891. Min Act: -0.0002

Data Index: 843394 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0904. Min Act: -0.0002

Data Index: 13516 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1195737 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0888. Min Act: -0.0002

Data Index: 497206 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1347225 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0956. Min Act: -0.0002

Data Index: 127483 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0890. Min Act: -0.0001

Data Index: 756032 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0856. Min Act: -0.0001

Data Index: 670458 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0877. Min Act: -0.0001

Data Index: 575164 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0836. Min Act: -0.0001

Data Index: 327348 (C4 (Web Text))

Max Activating Token Index: 506