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

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

Neuron 4769 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: 0.0725. Min Range: -0.0725

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1630305 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0608. Min Act: -0.0002

Data Index: 610209 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1247648 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1275657 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0508. Min Act: -0.0002

Data Index: 238540 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0485. Min Act: -0.0002

Data Index: 404771 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0476. Min Act: -0.0002

Data Index: 617289 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1276335 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0469. Min Act: -0.0002

Data Index: 598582 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1071701 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1077016 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0436. Min Act: -0.0002

Data Index: 206240 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1019149 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0461. Min Act: -0.0002

Data Index: 156928 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0425. Min Act: -0.0002

Data Index: 138035 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0441. Min Act: -0.0002

Data Index: 144132 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1182698 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0439. Min Act: -0.0002

Data Index: 479501 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1301247 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1091514 (C4 (Web Text))

Max Activating Token Index: 665