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

Dataset: The Pile

Neuron 768 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: 0.2986. Min Range: -0.2986

Max Act: 0.2939. Min Act: -0.0001

Data Index: 950875 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2986. Min Act: -0.0000

Data Index: 335679 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2799. Min Act: -0.0001

Data Index: 392747 (The Pile)

Max Activating Token Index: 75

Text #3

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1014847 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1485743 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2018. Min Act: -0.0000

Data Index: 492766 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2082. Min Act: -0.0000

Data Index: 716346 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1513493 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2056. Min Act: -0.0000

Data Index: 43288 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1985174 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1984. Min Act: -0.0000

Data Index: 321870 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1993. Min Act: -0.0001

Data Index: 1698405 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1090749 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1975. Min Act: -0.0000

Data Index: 748871 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1970. Min Act: -0.0001

Data Index: 384709 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1159 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1334962 (The Pile)

Max Activating Token Index: 340

Text #17

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1037461 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1070129 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1939. Min Act: -0.0000

Data Index: 871156 (The Pile)

Max Activating Token Index: 857