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

Dataset: The Pile

Neuron 834 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1972. Min Range: -1.1972

Max Act: 1.1972. Min Act: -0.0000

Data Index: 706301 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1900272 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.8214. Min Act: -0.0000

Data Index: 462506 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1749789 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.6595. Min Act: -0.0000

Data Index: 875134 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.8624. Min Act: -0.0000

Data Index: 332237 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1940798 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.9841. Min Act: -0.0000

Data Index: 506466 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1960323 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1297260 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1718554 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.6919. Min Act: -0.0000

Data Index: 16389 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1264744 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.6851. Min Act: -0.0000

Data Index: 77758 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.7126. Min Act: -0.0000

Data Index: 291616 (The Pile)

Max Activating Token Index: 539

Text #15

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.7225. Min Act: 0.0000

Data Index: 284669 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1061824 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.6401. Min Act: -0.0000

Data Index: 433607 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1544156 (The Pile)

Max Activating Token Index: 817

Text #19

Max Range: 1.1972. Min Range: -1.1972

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1313670 (The Pile)

Max Activating Token Index: 434