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

Dataset: The Pile

Neuron 1665 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: 1.9595. Min Range: -1.9595

Max Act: 1.9595. Min Act: -0.0000

Data Index: 521147 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.5956. Min Act: -0.0000

Data Index: 1627765 (The Pile)

Max Activating Token Index: 873

Text #2

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.5272. Min Act: -0.0000

Data Index: 521507 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.4805. Min Act: -0.0000

Data Index: 893059 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.5008. Min Act: -0.0000

Data Index: 1522455 (The Pile)

Max Activating Token Index: 979

Text #5

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.6687. Min Act: -0.0000

Data Index: 363726 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.4551. Min Act: -0.0000

Data Index: 960656 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.5958. Min Act: -0.0000

Data Index: 1966907 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1561934 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1754086 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.1635. Min Act: -0.0000

Data Index: 995266 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1891510 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1986627 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.3068. Min Act: -0.0000

Data Index: 277624 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.3584. Min Act: -0.0000

Data Index: 301076 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.3138. Min Act: -0.0000

Data Index: 970324 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1519265 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1061492 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.2148. Min Act: -0.0000

Data Index: 508725 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 1.9595. Min Range: -1.9595

Max Act: 1.0792. Min Act: -0.0000

Data Index: 747065 (The Pile)

Max Activating Token Index: 309