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

Dataset: The Pile

Neuron 3209 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: 0.4008. Min Range: -0.4008

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1290470 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3682. Min Act: -0.0000

Data Index: 733729 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1565084 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1867612 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2828. Min Act: -0.0000

Data Index: 974070 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1721966 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1022874 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1780014 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2705. Min Act: -0.0000

Data Index: 929780 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1213735 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1380948 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.1854. Min Act: -0.0000

Data Index: 610883 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2232. Min Act: -0.0000

Data Index: 465464 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2099. Min Act: -0.0000

Data Index: 122336 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2378. Min Act: -0.0000

Data Index: 514367 (The Pile)

Max Activating Token Index: 515

Text #15

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1033588 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1407245 (The Pile)

Max Activating Token Index: 273

Text #17

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1437289 (The Pile)

Max Activating Token Index: 963

Text #18

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1262347 (The Pile)

Max Activating Token Index: 345

Text #19

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1130734 (The Pile)

Max Activating Token Index: 205