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

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

Neuron 3 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.8228. Min Act: -0.0000

Data Index: 1348564 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.4703. Min Act: 0.0000

Data Index: 151384 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.6395. Min Act: -0.0000

Data Index: 1086487 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.2202. Min Act: -0.0000

Data Index: 403390 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.3328. Min Act: -0.0000

Data Index: 159843 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.0606. Min Act: -0.0000

Data Index: 722525 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.0201. Min Act: -0.0000

Data Index: 216092 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 5.8228. Min Range: -5.8228

Max Act: 4.5527. Min Act: -0.0000

Data Index: 317800 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.0189. Min Act: -0.0000

Data Index: 553376 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.3555. Min Act: -0.0000

Data Index: 352505 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 5.8228. Min Range: -5.8228

Max Act: 4.8264. Min Act: -0.0000

Data Index: 850218 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.1570. Min Act: 0.0000

Data Index: 584403 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 5.8228. Min Range: -5.8228

Max Act: 4.8837. Min Act: -0.0000

Data Index: 163737 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.2435. Min Act: -0.0000

Data Index: 107857 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 5.8228. Min Range: -5.8228

Max Act: 4.8486. Min Act: -0.0000

Data Index: 571039 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 5.8228. Min Range: -5.8228

Max Act: 5.0132. Min Act: -0.0000

Data Index: 420123 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 5.8228. Min Range: -5.8228

Max Act: 4.8320. Min Act: -0.0000

Data Index: 207200 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 5.8228. Min Range: -5.8228

Max Act: 4.6481. Min Act: -0.0000

Data Index: 173568 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 5.8228. Min Range: -5.8228

Max Act: 4.5988. Min Act: -0.0000

Data Index: 1346750 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 5.8228. Min Range: -5.8228

Max Act: 4.6902. Min Act: 0.0000

Data Index: 684299 (C4 (Web Text))

Max Activating Token Index: 562