Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3865 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1129467 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0393. Min Act: -0.0003

Data Index: 279820 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0326. Min Act: -0.0003

Data Index: 400957 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0398. Min Act: -0.0002

Data Index: 658271 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0380. Min Act: -0.0003

Data Index: 879021 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0360. Min Act: -0.0003

Data Index: 987954 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0324. Min Act: -0.0003

Data Index: 668964 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0357. Min Act: -0.0002

Data Index: 75448 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1062217 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1126121 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0353. Min Act: -0.0002

Data Index: 956856 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1030815 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0350. Min Act: -0.0002

Data Index: 820387 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0331. Min Act: -0.0003

Data Index: 362132 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0298. Min Act: -0.0002

Data Index: 185501 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0389. Min Act: -0.0002

Data Index: 236200 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0399. Min Act: -0.0002

Data Index: 33005 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0332. Min Act: -0.0002

Data Index: 715882 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0348. Min Act: -0.0003

Data Index: 79033 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0345. Min Act: -0.0002

Data Index: 5234 (C4 (Web Text))

Max Activating Token Index: 321