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

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

Neuron 2307 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.8880. Min Act: -0.0000

Data Index: 728502 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.8772. Min Act: -0.0000

Data Index: 600884 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6953. Min Act: -0.0000

Data Index: 10777 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6385. Min Act: -0.0000

Data Index: 267503 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5863. Min Act: -0.0000

Data Index: 1349448 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6420. Min Act: -0.0000

Data Index: 844714 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4408. Min Act: -0.0000

Data Index: 238921 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6009. Min Act: -0.0000

Data Index: 698467 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6006. Min Act: -0.0000

Data Index: 320781 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5195. Min Act: -0.0000

Data Index: 869698 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4916. Min Act: -0.0000

Data Index: 213703 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1481668 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5648. Min Act: -0.0000

Data Index: 1056780 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.3882. Min Act: -0.0000

Data Index: 246926 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.3630. Min Act: -0.0000

Data Index: 1439520 (Python Code)

Max Activating Token Index: 944

Text #15

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.3634. Min Act: -0.0000

Data Index: 985671 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4476. Min Act: -0.0000

Data Index: 1428301 (Python Code)

Max Activating Token Index: 772

Text #17

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5271. Min Act: -0.0000

Data Index: 717091 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4381. Min Act: -0.0000

Data Index: 386255 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5200. Min Act: -0.0000

Data Index: 596483 (C4 (Web Text))

Max Activating Token Index: 810