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

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

Neuron 5760 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: 2.3238. Min Range: -2.3238

Max Act: 2.3238. Min Act: -0.0000

Data Index: 1358907 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 2.3238. Min Range: -2.3238

Max Act: 2.0931. Min Act: -0.0000

Data Index: 551448 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.9483. Min Act: -0.0000

Data Index: 36948 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 2.3238. Min Range: -2.3238

Max Act: 2.0598. Min Act: -0.0000

Data Index: 150091 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 2.3238. Min Range: -2.3238

Max Act: 2.0346. Min Act: -0.0000

Data Index: 398047 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.9954. Min Act: -0.0000

Data Index: 666083 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.9637. Min Act: -0.0000

Data Index: 1295607 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.8615. Min Act: -0.0000

Data Index: 1258623 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.9470. Min Act: -0.0000

Data Index: 260310 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.9517. Min Act: -0.0000

Data Index: 1337519 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.8528. Min Act: -0.0000

Data Index: 949581 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.9535. Min Act: -0.0000

Data Index: 148366 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.9169. Min Act: -0.0000

Data Index: 1591021 (Python Code)

Max Activating Token Index: 926

Text #13

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.8876. Min Act: -0.0000

Data Index: 743594 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.7752. Min Act: -0.0000

Data Index: 1246685 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.8772. Min Act: -0.0000

Data Index: 37057 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.8582. Min Act: -0.0000

Data Index: 475793 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.9618. Min Act: -0.0000

Data Index: 1428972 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.8568. Min Act: -0.0000

Data Index: 1090609 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.7413. Min Act: -0.0000

Data Index: 1484524 (Python Code)

Max Activating Token Index: 306