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

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

Neuron 3021 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1482151 (Python Code)

Max Activating Token Index: 76

Text #1

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1516. Min Act: -0.0000

Data Index: 1498240 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1478361 (Python Code)

Max Activating Token Index: 770

Text #3

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.2042. Min Act: -0.0000

Data Index: 1527437 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1420233 (Python Code)

Max Activating Token Index: 566

Text #5

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0966. Min Act: -0.0000

Data Index: 1526905 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1398. Min Act: -0.0000

Data Index: 134751 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1495470 (Python Code)

Max Activating Token Index: 938

Text #8

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1439235 (Python Code)

Max Activating Token Index: 525

Text #9

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1508475 (Python Code)

Max Activating Token Index: 476

Text #10

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1457147 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1594924 (Python Code)

Max Activating Token Index: 143

Text #12

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1650843 (Python Code)

Max Activating Token Index: 284

Text #13

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1507603 (Python Code)

Max Activating Token Index: 529

Text #14

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1495272 (Python Code)

Max Activating Token Index: 805

Text #15

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1325375 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1548603 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1419771 (Python Code)

Max Activating Token Index: 1022

Text #18

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1403318 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1517075 (Python Code)

Max Activating Token Index: 452