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

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

Neuron 637 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0430. Min Act: -0.0003

Data Index: 287425 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0417. Min Act: -0.0003

Data Index: 458287 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0385. Min Act: -0.0002

Data Index: 592901 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0389. Min Act: -0.0004

Data Index: 839866 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1264171 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0375. Min Act: -0.0003

Data Index: 790525 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0357. Min Act: -0.0003

Data Index: 458251 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1111236 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0350. Min Act: -0.0003

Data Index: 367213 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0341. Min Act: -0.0002

Data Index: 919070 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0338. Min Act: -0.0003

Data Index: 920183 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0339. Min Act: -0.0003

Data Index: 215517 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0337. Min Act: -0.0003

Data Index: 131930 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0330. Min Act: -0.0002

Data Index: 730536 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0326. Min Act: -0.0004

Data Index: 454308 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0340. Min Act: -0.0003

Data Index: 742334 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0332. Min Act: -0.0004

Data Index: 1098603 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1103602 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1086713 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1172644 (C4 (Web Text))

Max Activating Token Index: 819