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

Dataset: The Pile

Neuron 3226 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.5263. Min Act: -0.0000

Data Index: 494589 (The Pile)

Max Activating Token Index: 626

Text #1

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4888. Min Act: -0.0000

Data Index: 55052 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4358. Min Act: -0.0000

Data Index: 206944 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4299. Min Act: -0.0000

Data Index: 372877 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3976. Min Act: -0.0000

Data Index: 889515 (The Pile)

Max Activating Token Index: 727

Text #5

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1839843 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1468456 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1603318 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1979548 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3286. Min Act: -0.0000

Data Index: 434886 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1813692 (The Pile)

Max Activating Token Index: 710

Text #11

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1091958 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3286. Min Act: -0.0000

Data Index: 494636 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3390. Min Act: -0.0000

Data Index: 659743 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3194. Min Act: -0.0000

Data Index: 939817 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3094. Min Act: -0.0000

Data Index: 87957 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1138546 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1820077 (The Pile)

Max Activating Token Index: 586

Text #18

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1218509 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1251804 (The Pile)

Max Activating Token Index: 281