Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1499 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1656. Min Act: -0.0000

Data Index: 539534 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1790. Min Act: -0.0000

Data Index: 737419 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1533. Min Act: -0.0000

Data Index: 365816 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1504. Min Act: -0.0000

Data Index: 706449 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1477. Min Act: -0.0000

Data Index: 115285 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1449. Min Act: -0.0000

Data Index: 619057 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1406. Min Act: -0.0000

Data Index: 647351 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1207. Min Act: -0.0000

Data Index: 183105 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1219396 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1279. Min Act: -0.0000

Data Index: 119364 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1236. Min Act: -0.0000

Data Index: 92037 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1043539 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1229. Min Act: -0.0000

Data Index: 318591 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1288. Min Act: -0.0000

Data Index: 669490 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1199. Min Act: -0.0000

Data Index: 901644 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1148. Min Act: -0.0000

Data Index: 551160 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1275. Min Act: -0.0000

Data Index: 84149 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1264. Min Act: -0.0000

Data Index: 491282 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1155. Min Act: -0.0000

Data Index: 105156 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1181. Min Act: -0.0000

Data Index: 367812 (C4 (Web Text))

Max Activating Token Index: 130