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

Dataset: The Pile

Neuron 2260 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1432536 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1783091 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1770078 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1266629 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1820154 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3374. Min Act: -0.0000

Data Index: 226153 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1551338 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3280. Min Act: -0.0000

Data Index: 935605 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1594656 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1702767 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3071. Min Act: -0.0000

Data Index: 500974 (The Pile)

Max Activating Token Index: 405

Text #11

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1140376 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1630563 (The Pile)

Max Activating Token Index: 718

Text #13

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1273256 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.2737. Min Act: -0.0000

Data Index: 395404 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1543354 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.3321. Min Act: -0.0000

Data Index: 847178 (The Pile)

Max Activating Token Index: 647

Text #17

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1784839 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1320067 (The Pile)

Max Activating Token Index: 219

Text #19

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1464711 (The Pile)

Max Activating Token Index: 636