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

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

Neuron 2958 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1375448 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1285003 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0349. Min Act: -0.0002

Data Index: 348587 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1459144 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0334. Min Act: -0.0002

Data Index: 470632 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1590462 (Python Code)

Max Activating Token Index: 476

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1517758 (Python Code)

Max Activating Token Index: 563

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1108649 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1101847 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1518089 (Python Code)

Max Activating Token Index: 298

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1649793 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1555834 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1453495 (Python Code)

Max Activating Token Index: 806

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1100450 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1591872 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1614956 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0297. Min Act: -0.0002

Data Index: 671882 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0281. Min Act: -0.0002

Data Index: 405757 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1401371 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1422784 (Python Code)

Max Activating Token Index: 646