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

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

Neuron 993 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0003

Data Index: 247170 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0328. Min Act: -0.0003

Data Index: 829580 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1302050 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0264. Min Act: -0.0003

Data Index: 784161 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0281. Min Act: -0.0003

Data Index: 65413 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1229449 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1205799 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0262. Min Act: -0.0003

Data Index: 553347 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0254. Min Act: -0.0003

Data Index: 344938 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0262. Min Act: -0.0003

Data Index: 850584 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0256. Min Act: -0.0003

Data Index: 495734 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0261. Min Act: -0.0003

Data Index: 745126 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0263. Min Act: -0.0003

Data Index: 366465 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0250. Min Act: -0.0003

Data Index: 127558 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1331770 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0264. Min Act: -0.0003

Data Index: 36911 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1188827 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0244. Min Act: -0.0003

Data Index: 86158 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0237. Min Act: -0.0003

Data Index: 924401 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0235. Min Act: -0.0003

Data Index: 852317 (C4 (Web Text))

Max Activating Token Index: 312