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

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

Neuron 1808 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.6388. Min Range: -11.6388

Max Act: 11.6388. Min Act: -0.0000

Data Index: 171368 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 11.6388. Min Range: -11.6388

Max Act: 11.3522. Min Act: -0.0000

Data Index: 1229762 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 11.6388. Min Range: -11.6388

Max Act: 10.8564. Min Act: -0.0000

Data Index: 646262 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 11.6388. Min Range: -11.6388

Max Act: 10.8152. Min Act: -0.0000

Data Index: 927953 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.9291. Min Act: -0.0000

Data Index: 550302 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 11.6388. Min Range: -11.6388

Max Act: 10.0537. Min Act: -0.0000

Data Index: 938435 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 11.6388. Min Range: -11.6388

Max Act: 10.1838. Min Act: -0.0000

Data Index: 421663 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.7551. Min Act: -0.0000

Data Index: 112641 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.7853. Min Act: -0.0000

Data Index: 608387 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 11.6388. Min Range: -11.6388

Max Act: 10.0467. Min Act: -0.0000

Data Index: 507563 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.5514. Min Act: -0.0000

Data Index: 514282 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.7549. Min Act: -0.0000

Data Index: 217370 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.1331. Min Act: -0.0000

Data Index: 294773 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.7055. Min Act: -0.0000

Data Index: 404396 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.8295. Min Act: 0.0001

Data Index: 1288638 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.0585. Min Act: -0.0000

Data Index: 205179 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.2321. Min Act: -0.0000

Data Index: 66552 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.6477. Min Act: -0.0000

Data Index: 1049241 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.4446. Min Act: -0.0000

Data Index: 772983 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 11.6388. Min Range: -11.6388

Max Act: 9.2506. Min Act: -0.0000

Data Index: 562806 (C4 (Web Text))

Max Activating Token Index: 736