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

Dataset: The Pile

Neuron 3156 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.3183. Min Act: -0.0000

Data Index: 1538450 (The Pile)

Max Activating Token Index: 336

Text #1

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1635536 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1452716 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1942493 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1052356 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1042285 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1172414 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1589. Min Act: -0.0000

Data Index: 1125311 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1169. Min Act: -0.0000

Data Index: 61068 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1481. Min Act: -0.0000

Data Index: 165972 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1549637 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9883. Min Act: -0.0000

Data Index: 4783 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9657. Min Act: -0.0000

Data Index: 682874 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1706903 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1641934 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8976. Min Act: -0.0000

Data Index: 741387 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1333121 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1631723 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1958043 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9052. Min Act: -0.0000

Data Index: 528536 (The Pile)

Max Activating Token Index: 731