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

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

Neuron 470 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1542677 (Python Code)

Max Activating Token Index: 590

Text #1

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.6282. Min Act: -0.0000

Data Index: 900040 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.5244. Min Act: -0.0000

Data Index: 1247304 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.3699. Min Act: -0.0000

Data Index: 1100989 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1956. Min Act: -0.0000

Data Index: 118989 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1699. Min Act: -0.0000

Data Index: 404284 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1884. Min Act: -0.0000

Data Index: 1638564 (Python Code)

Max Activating Token Index: 963

Text #7

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1153. Min Act: -0.0000

Data Index: 971829 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.2123. Min Act: -0.0000

Data Index: 395159 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1280370 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1393. Min Act: -0.0000

Data Index: 765405 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1192845 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1564. Min Act: -0.0000

Data Index: 673417 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1188847 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1229830 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1062. Min Act: -0.0000

Data Index: 237982 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1277. Min Act: -0.0000

Data Index: 304293 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1037292 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.1202. Min Act: -0.0000

Data Index: 167001 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.6282. Min Range: -1.6282

Max Act: 1.0752. Min Act: -0.0000

Data Index: 943870 (C4 (Web Text))

Max Activating Token Index: 37