Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1028 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0006

Data Index: 750070 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1304598 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0356. Min Act: -0.0006

Data Index: 1174100 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0351. Min Act: -0.0006

Data Index: 363425 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0341. Min Act: -0.0006

Data Index: 1048183 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0346. Min Act: -0.0006

Data Index: 533595 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0346. Min Act: -0.0006

Data Index: 133154 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0344. Min Act: -0.0006

Data Index: 632389 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0342. Min Act: -0.0006

Data Index: 600661 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0339. Min Act: -0.0006

Data Index: 1129125 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1022164 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1304138 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0319. Min Act: -0.0006

Data Index: 891862 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0319. Min Act: -0.0006

Data Index: 477812 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0319. Min Act: -0.0006

Data Index: 1320614 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0309. Min Act: -0.0005

Data Index: 1181802 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0307. Min Act: -0.0006

Data Index: 688409 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0318. Min Act: -0.0006

Data Index: 111348 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0312. Min Act: -0.0006

Data Index: 320751 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0309. Min Act: -0.0006

Data Index: 94783 (C4 (Web Text))

Max Activating Token Index: 91