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

Dataset: The Pile

Neuron 4474 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: 1.2922. Min Range: -1.2922

Max Act: 1.2922. Min Act: -0.0000

Data Index: 897982 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1334588 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1477266 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1454582 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.1594. Min Act: -0.0000

Data Index: 456436 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.1315. Min Act: -0.0000

Data Index: 1037888 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.1111. Min Act: -0.0000

Data Index: 77609 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0622. Min Act: -0.0000

Data Index: 897029 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1178570 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0398. Min Act: -0.0000

Data Index: 45210 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0277. Min Act: -0.0000

Data Index: 233051 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9768. Min Act: -0.0000

Data Index: 616295 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1989114 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0081. Min Act: -0.0000

Data Index: 86679 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1305829 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9168. Min Act: -0.0000

Data Index: 120008 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8811. Min Act: -0.0000

Data Index: 854992 (The Pile)

Max Activating Token Index: 803

Text #17

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8654. Min Act: -0.0000

Data Index: 343087 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8405. Min Act: -0.0000

Data Index: 500385 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1419317 (The Pile)

Max Activating Token Index: 419