Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 460 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1948. Min Act: -0.0000

Data Index: 650176 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9839. Min Act: -0.0000

Data Index: 228403 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9573. Min Act: -0.0000

Data Index: 425167 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9169. Min Act: -0.0000

Data Index: 51817 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1144141 (The Pile)

Max Activating Token Index: 137

Text #5

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1265480 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9031. Min Act: -0.0000

Data Index: 280915 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1312943 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1192002 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7684. Min Act: -0.0000

Data Index: 279894 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7910. Min Act: -0.0000

Data Index: 620605 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8577. Min Act: -0.0000

Data Index: 559977 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1264986 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7189. Min Act: -0.0000

Data Index: 4277 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7224. Min Act: -0.0000

Data Index: 7890 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7355. Min Act: -0.0000

Data Index: 735550 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1564703 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1245261 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7374. Min Act: 0.0000

Data Index: 775535 (The Pile)

Max Activating Token Index: 438

Text #19

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1591298 (The Pile)

Max Activating Token Index: 865