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

Dataset: The Pile

Neuron 3430 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.8188. Min Act: -0.0000

Data Index: 1554271 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.9097. Min Act: -0.0000

Data Index: 931273 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1144709 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.6204. Min Act: -0.0000

Data Index: 275162 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.5024. Min Act: -0.0000

Data Index: 803082 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.5871. Min Act: -0.0000

Data Index: 620832 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.4787. Min Act: -0.0000

Data Index: 1371377 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.3894. Min Act: -0.0000

Data Index: 461045 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.5571. Min Act: -0.0000

Data Index: 380412 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1972006 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.3188. Min Act: -0.0000

Data Index: 1728290 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.3662. Min Act: -0.0000

Data Index: 590240 (The Pile)

Max Activating Token Index: 514

Text #12

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.2927. Min Act: -0.0000

Data Index: 384214 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.4178. Min Act: -0.0000

Data Index: 862619 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.3414. Min Act: -0.0000

Data Index: 198470 (The Pile)

Max Activating Token Index: 879

Text #15

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.4329. Min Act: -0.0000

Data Index: 1539400 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.4004. Min Act: -0.0000

Data Index: 999375 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.2353. Min Act: -0.0000

Data Index: 993819 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1123179 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.4821. Min Act: -0.0000

Data Index: 1872339 (The Pile)

Max Activating Token Index: 723