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

Dataset: The Pile

Neuron 485 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.4019. Min Act: -0.0000

Data Index: 134155 (The Pile)

Max Activating Token Index: 863

Text #1

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3804. Min Act: -0.0000

Data Index: 771508 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3078. Min Act: -0.0000

Data Index: 425050 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1027871 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3242. Min Act: -0.0000

Data Index: 988342 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3454. Min Act: -0.0000

Data Index: 585423 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1432359 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3112. Min Act: -0.0000

Data Index: 36221 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3067. Min Act: -0.0000

Data Index: 865793 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2917. Min Act: -0.0000

Data Index: 394950 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3020. Min Act: -0.0000

Data Index: 213532 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1989714 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3066. Min Act: -0.0000

Data Index: 622051 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2919. Min Act: -0.0000

Data Index: 357079 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2644. Min Act: -0.0000

Data Index: 784128 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2905. Min Act: -0.0000

Data Index: 255585 (The Pile)

Max Activating Token Index: 834

Text #16

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1132154 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1399306 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1537773 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2681. Min Act: -0.0000

Data Index: 606864 (The Pile)

Max Activating Token Index: 850