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

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

Neuron 5608 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: 1.1895. Min Range: -1.1895

Max Act: 1.1895. Min Act: -0.0000

Data Index: 974204 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.9980. Min Act: -0.0000

Data Index: 403312 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.9548. Min Act: -0.0000

Data Index: 977666 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.9374. Min Act: -0.0000

Data Index: 103420 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.8684. Min Act: -0.0000

Data Index: 354004 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.8661. Min Act: -0.0000

Data Index: 847028 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1227621 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.8483. Min Act: -0.0000

Data Index: 541223 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7917. Min Act: -0.0000

Data Index: 137268 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.8109. Min Act: -0.0000

Data Index: 292530 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1269078 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1093678 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.8121. Min Act: -0.0000

Data Index: 204538 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7527. Min Act: -0.0000

Data Index: 931926 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7995. Min Act: -0.0000

Data Index: 349476 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7786. Min Act: -0.0000

Data Index: 355436 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1346708 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7421. Min Act: -0.0000

Data Index: 295472 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7395. Min Act: -0.0000

Data Index: 280789 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7385. Min Act: -0.0000

Data Index: 254412 (C4 (Web Text))

Max Activating Token Index: 109