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

Dataset: The Pile

Neuron 2404 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.6207. Min Act: -0.0000

Data Index: 845210 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4290. Min Act: -0.0000

Data Index: 350644 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4856. Min Act: -0.0000

Data Index: 334849 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3656. Min Act: -0.0000

Data Index: 593473 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1842739 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3826. Min Act: -0.0000

Data Index: 233707 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4053. Min Act: -0.0000

Data Index: 1495872 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3238. Min Act: -0.0000

Data Index: 1891605 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4343. Min Act: -0.0000

Data Index: 1437467 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1859740 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3697. Min Act: -0.0000

Data Index: 526038 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3155. Min Act: -0.0000

Data Index: 180896 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1785686 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3034. Min Act: -0.0000

Data Index: 806934 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1960934 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1130295 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.1931. Min Act: -0.0000

Data Index: 581083 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1421203 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1477324 (The Pile)

Max Activating Token Index: 749

Text #19

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.1535. Min Act: -0.0000

Data Index: 666884 (The Pile)

Max Activating Token Index: 10