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

Dataset: The Pile

Neuron 1812 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3716. Min Act: -0.0000

Data Index: 907210 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3671. Min Act: -0.0000

Data Index: 827134 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1354912 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3245. Min Act: -0.0000

Data Index: 940864 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1059649 (The Pile)

Max Activating Token Index: 197

Text #5

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1849888 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3018. Min Act: -0.0000

Data Index: 792959 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3076. Min Act: 0.0000

Data Index: 1440573 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2859. Min Act: -0.0000

Data Index: 982089 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2879. Min Act: -0.0000

Data Index: 52072 (The Pile)

Max Activating Token Index: 562

Text #10

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2726. Min Act: -0.0000

Data Index: 366766 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2915. Min Act: -0.0000

Data Index: 404622 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2836. Min Act: -0.0000

Data Index: 856932 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1999188 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1638267 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2966. Min Act: -0.0000

Data Index: 990804 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2856. Min Act: -0.0000

Data Index: 207309 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1776477 (The Pile)

Max Activating Token Index: 277

Text #18

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2656. Min Act: -0.0000

Data Index: 78399 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1837759 (The Pile)

Max Activating Token Index: 11