Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2812 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 16931 (The Pile)

Max Activating Token Index: 191

Text #1

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 485598 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1819156 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1822588 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1987815 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 569318 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 955601 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1347111 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 105939 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 296724 (The Pile)

Max Activating Token Index: 113

Text #10

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1961530 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1727719 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 336833 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1522327 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 771423 (The Pile)

Max Activating Token Index: 153

Text #15

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 671600 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1850473 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 401455 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 738827 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 745235 (The Pile)

Max Activating Token Index: 192