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

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

Neuron 1511 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: 0.0719. Min Range: -0.0719

Max Act: 0.0719. Min Act: -0.0003

Data Index: 412013 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0595. Min Act: -0.0003

Data Index: 571506 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0526. Min Act: -0.0003

Data Index: 802781 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1029379 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0418. Min Act: -0.0003

Data Index: 601476 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1258251 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1293524 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0369. Min Act: -0.0003

Data Index: 461107 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0346. Min Act: -0.0003

Data Index: 475779 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1062985 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0333. Min Act: -0.0003

Data Index: 635095 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0345. Min Act: -0.0003

Data Index: 739770 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0344. Min Act: -0.0003

Data Index: 723502 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0327. Min Act: -0.0003

Data Index: 474870 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0334. Min Act: -0.0003

Data Index: 758159 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0341. Min Act: -0.0003

Data Index: 810412 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0322. Min Act: -0.0003

Data Index: 76820 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0326. Min Act: -0.0003

Data Index: 315627 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0312. Min Act: -0.0003

Data Index: 344600 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0322. Min Act: -0.0003

Data Index: 574406 (C4 (Web Text))

Max Activating Token Index: 931