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

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

Neuron 1084 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1039888 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1659. Min Act: -0.0000

Data Index: 577729 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1541. Min Act: -0.0000

Data Index: 203491 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1072823 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1208. Min Act: -0.0000

Data Index: 756456 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1212706 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1408. Min Act: -0.0000

Data Index: 430198 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1093379 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1321. Min Act: -0.0000

Data Index: 923569 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1385. Min Act: -0.0000

Data Index: 177831 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1429. Min Act: -0.0000

Data Index: 840420 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1486. Min Act: -0.0001

Data Index: 920069 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1345. Min Act: -0.0000

Data Index: 761414 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1388. Min Act: -0.0000

Data Index: 327584 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1237. Min Act: -0.0000

Data Index: 560849 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1299. Min Act: -0.0000

Data Index: 845479 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1302658 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1284. Min Act: -0.0000

Data Index: 420297 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1257. Min Act: -0.0000

Data Index: 193217 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1096512 (C4 (Web Text))

Max Activating Token Index: 1006