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

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

Neuron 4861 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: 0.5068. Min Range: -0.5068

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1337972 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1339533 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3859. Min Act: -0.0000

Data Index: 137159 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3557. Min Act: -0.0000

Data Index: 227961 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3566. Min Act: -0.0000

Data Index: 630756 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3333. Min Act: -0.0000

Data Index: 630233 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3364. Min Act: -0.0000

Data Index: 562255 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1014101 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3550. Min Act: -0.0000

Data Index: 751843 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3565. Min Act: -0.0000

Data Index: 754687 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3302. Min Act: -0.0000

Data Index: 423471 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1329458 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3416. Min Act: -0.0000

Data Index: 818452 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3303. Min Act: -0.0000

Data Index: 380258 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3181. Min Act: -0.0000

Data Index: 173922 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3255. Min Act: -0.0000

Data Index: 64940 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3272. Min Act: -0.0000

Data Index: 403018 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3161. Min Act: -0.0000

Data Index: 519016 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3121. Min Act: -0.0000

Data Index: 451114 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3244. Min Act: -0.0000

Data Index: 732741 (C4 (Web Text))

Max Activating Token Index: 389