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

Dataset: The Pile

Neuron 4087 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.8874. Min Act: -0.0000

Data Index: 1045102 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.7055. Min Act: -0.0000

Data Index: 1492890 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.3622. Min Act: -0.0000

Data Index: 641536 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.5996. Min Act: -0.0000

Data Index: 1211377 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.5822. Min Act: -0.0000

Data Index: 94965 (The Pile)

Max Activating Token Index: 785

Text #5

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.2823. Min Act: -0.0000

Data Index: 648282 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.2912. Min Act: -0.0000

Data Index: 1504657 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.6888. Min Act: -0.0000

Data Index: 361450 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.2818. Min Act: -0.0000

Data Index: 585212 (The Pile)

Max Activating Token Index: 984

Text #9

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.3073. Min Act: -0.0000

Data Index: 444259 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1004808 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.0867. Min Act: -0.0000

Data Index: 182636 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1077253 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 3.8874. Min Range: -3.8874

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1883739 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 3.8874. Min Range: -3.8874

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1381546 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 3.8874. Min Range: -3.8874

Max Act: 0.9661. Min Act: -0.0000

Data Index: 121114 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.1040. Min Act: -0.0000

Data Index: 870532 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 3.8874. Min Range: -3.8874

Max Act: 1.0798. Min Act: -0.0000

Data Index: 1524460 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 3.8874. Min Range: -3.8874

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1575315 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 3.8874. Min Range: -3.8874

Max Act: 0.9153. Min Act: -0.0000

Data Index: 587029 (The Pile)

Max Activating Token Index: 617