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

Dataset: The Pile

Neuron 4397 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: 0.5150. Min Range: -0.5150

Max Act: 0.5150. Min Act: -0.0000

Data Index: 350538 (The Pile)

Max Activating Token Index: 484

Text #1

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4842. Min Act: -0.0000

Data Index: 513997 (The Pile)

Max Activating Token Index: 938

Text #2

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4089. Min Act: -0.0000

Data Index: 35521 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3819. Min Act: -0.0000

Data Index: 49202 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3666. Min Act: -0.0000

Data Index: 421926 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1420060 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4022. Min Act: -0.0000

Data Index: 289026 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1027722 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4445. Min Act: -0.0000

Data Index: 900878 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1039305 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1997319 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3452. Min Act: -0.0000

Data Index: 468171 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3378. Min Act: -0.0000

Data Index: 889923 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1293170 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3528. Min Act: -0.0000

Data Index: 627421 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1956668 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1127706 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1957224 (The Pile)

Max Activating Token Index: 765

Text #18

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1689988 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1338811 (The Pile)

Max Activating Token Index: 141