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

Dataset: The Pile

Neuron 3035 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: 0.3561. Min Range: -0.3561

Max Act: 0.3472. Min Act: -0.0000

Data Index: 517729 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1447125 (The Pile)

Max Activating Token Index: 160

Text #2

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1471750 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.3057. Min Act: -0.0000

Data Index: 519165 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2988. Min Act: -0.0000

Data Index: 794312 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1675199 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.3180. Min Act: -0.0000

Data Index: 807263 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.3080. Min Act: -0.0000

Data Index: 265695 (The Pile)

Max Activating Token Index: 128

Text #8

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.3129. Min Act: -0.0000

Data Index: 917767 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1357272 (The Pile)

Max Activating Token Index: 778

Text #10

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1613188 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2945. Min Act: -0.0000

Data Index: 856047 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2836. Min Act: -0.0000

Data Index: 315063 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2819. Min Act: -0.0000

Data Index: 935421 (The Pile)

Max Activating Token Index: 947

Text #14

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2806. Min Act: -0.0000

Data Index: 106179 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2892. Min Act: -0.0000

Data Index: 823184 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2954. Min Act: -0.0000

Data Index: 671917 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1382736 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1500466 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1610695 (The Pile)

Max Activating Token Index: 1004