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

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

Neuron 4598 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: 0.0362. Min Act: -0.0002

Data Index: 1000874 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0359. Min Act: -0.0002

Data Index: 482722 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0359. Min Act: -0.0002

Data Index: 694398 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1153982 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0346. Min Act: -0.0002

Data Index: 174839 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1263295 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0336. Min Act: -0.0002

Data Index: 794040 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0329. Min Act: -0.0002

Data Index: 790004 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0329. Min Act: -0.0002

Data Index: 643299 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1184596 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0323. Min Act: -0.0002

Data Index: 531165 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1338611 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0322. Min Act: -0.0002

Data Index: 728349 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0321. Min Act: -0.0002

Data Index: 217525 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0321. Min Act: -0.0002

Data Index: 312236 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0320. Min Act: -0.0002

Data Index: 676279 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1352649 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0319. Min Act: -0.0002

Data Index: 88244 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0318. Min Act: -0.0002

Data Index: 76969 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0317. Min Act: -0.0002

Data Index: 79560 (C4 (Web Text))

Max Activating Token Index: 245