Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3920 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.8341. Min Act: -0.0000

Data Index: 1623552 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.7404. Min Act: -0.0000

Data Index: 177674 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.6143. Min Act: -0.0000

Data Index: 1833290 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5653. Min Act: -0.0000

Data Index: 452126 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5878. Min Act: -0.0000

Data Index: 941558 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5133. Min Act: -0.0000

Data Index: 1156019 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1340198 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4845. Min Act: -0.0000

Data Index: 840546 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3804. Min Act: -0.0000

Data Index: 661542 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3345. Min Act: -0.0000

Data Index: 1773462 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3202. Min Act: -0.0000

Data Index: 790944 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1504133 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3041. Min Act: -0.0000

Data Index: 213281 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1591318 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3929. Min Act: -0.0000

Data Index: 1332802 (The Pile)

Max Activating Token Index: 996

Text #15

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.2237. Min Act: -0.0000

Data Index: 292998 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.2901. Min Act: -0.0000

Data Index: 155227 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.1013. Min Act: -0.0000

Data Index: 71492 (The Pile)

Max Activating Token Index: 81

Text #18

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.2125. Min Act: -0.0000

Data Index: 1533000 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.2396. Min Act: -0.0000

Data Index: 999441 (The Pile)

Max Activating Token Index: 273