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

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

Neuron 3247 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8798. Min Act: -0.0000

Data Index: 566438 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.5484. Min Act: -0.0000

Data Index: 531967 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.5205. Min Act: -0.0000

Data Index: 237008 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.2091. Min Act: -0.0000

Data Index: 907991 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.1801. Min Act: -0.0000

Data Index: 41451 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.2306. Min Act: -0.0000

Data Index: 125624 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.1808. Min Act: -0.0000

Data Index: 641043 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.1274. Min Act: -0.0000

Data Index: 854613 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.1439. Min Act: -0.0000

Data Index: 1194059 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.2115. Min Act: -0.0000

Data Index: 742925 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.0953. Min Act: -0.0000

Data Index: 756626 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.0896. Min Act: -0.0000

Data Index: 490527 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.2053. Min Act: -0.0000

Data Index: 1201030 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.0922. Min Act: -0.0000

Data Index: 8841 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.0708. Min Act: -0.0000

Data Index: 1221635 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.0568. Min Act: -0.0000

Data Index: 661469 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.0426. Min Act: -0.0000

Data Index: 1298765 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.0488. Min Act: -0.0000

Data Index: 1183307 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 2.8798. Min Range: -2.8798

Max Act: 1.9254. Min Act: -0.0000

Data Index: 32072 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 2.8798. Min Range: -2.8798

Max Act: 1.9297. Min Act: -0.0000

Data Index: 606017 (C4 (Web Text))

Max Activating Token Index: 208