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

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

Neuron 754 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2242. Min Act: -0.0000

Data Index: 350862 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1087995 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1510. Min Act: -0.0000

Data Index: 833281 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1524. Min Act: -0.0000

Data Index: 505461 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1545. Min Act: -0.0001

Data Index: 522463 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1651025 (Python Code)

Max Activating Token Index: 610

Text #6

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1400. Min Act: -0.0000

Data Index: 870677 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1345. Min Act: 0.0000

Data Index: 907983 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1292587 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1289349 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1010858 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1382. Min Act: -0.0000

Data Index: 184904 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1321. Min Act: 0.0000

Data Index: 1280499 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1307. Min Act: -0.0000

Data Index: 725420 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1281. Min Act: 0.0000

Data Index: 147785 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1187861 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1244. Min Act: -0.0000

Data Index: 857604 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1172. Min Act: -0.0000

Data Index: 983349 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1494657 (Python Code)

Max Activating Token Index: 119

Text #19

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1191. Min Act: -0.0001

Data Index: 814948 (C4 (Web Text))

Max Activating Token Index: 310