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

Dataset: The Pile

Neuron 2174 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: 0.1765. Min Range: -0.1765

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1072659 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1175. Min Act: -0.0000

Data Index: 574133 (The Pile)

Max Activating Token Index: 545

Text #2

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1152852 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1078. Min Act: -0.0000

Data Index: 582532 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1151. Min Act: -0.0000

Data Index: 968433 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1582725 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1047. Min Act: -0.0000

Data Index: 724104 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1611362 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1072. Min Act: -0.0000

Data Index: 606285 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.0966. Min Act: -0.0000

Data Index: 342186 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1101. Min Act: -0.0000

Data Index: 356932 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1139. Min Act: -0.0000

Data Index: 950004 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1001. Min Act: -0.0000

Data Index: 818027 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1071. Min Act: -0.0000

Data Index: 373078 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.0992. Min Act: -0.0000

Data Index: 3646 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1113798 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1047. Min Act: -0.0000

Data Index: 656308 (The Pile)

Max Activating Token Index: 952

Text #17

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1135540 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.0934. Min Act: -0.0000

Data Index: 818524 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1586593 (The Pile)

Max Activating Token Index: 735