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

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

Neuron 662 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0355. Min Act: -0.0002

Data Index: 850504 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 664224 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0361. Min Act: -0.0002

Data Index: 121960 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0360. Min Act: -0.0002

Data Index: 933533 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0352. Min Act: -0.0002

Data Index: 183903 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0352. Min Act: -0.0002

Data Index: 858924 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1320336 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1075913 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0342. Min Act: -0.0002

Data Index: 781276 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1238644 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0337. Min Act: -0.0002

Data Index: 461514 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0342. Min Act: -0.0002

Data Index: 134316 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1053558 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1318591 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0332. Min Act: -0.0002

Data Index: 518811 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0328. Min Act: -0.0002

Data Index: 437843 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0327. Min Act: -0.0002

Data Index: 806777 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0320. Min Act: -0.0002

Data Index: 345257 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0002

Data Index: 410993 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1220959 (C4 (Web Text))

Max Activating Token Index: 665