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

Dataset: The Pile

Neuron 2505 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: 0.2805. Min Range: -0.2805

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1385662 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2592. Min Act: -0.0000

Data Index: 819385 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2805. Min Act: -0.0000

Data Index: 166619 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1996712 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2119. Min Act: -0.0000

Data Index: 539223 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2288. Min Act: -0.0000

Data Index: 872760 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2180. Min Act: -0.0000

Data Index: 813554 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2157. Min Act: -0.0000

Data Index: 500899 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2022. Min Act: -0.0000

Data Index: 376646 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1322668 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1495620 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2049. Min Act: -0.0000

Data Index: 244739 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1053298 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1944. Min Act: -0.0000

Data Index: 294744 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1992. Min Act: -0.0000

Data Index: 591939 (The Pile)

Max Activating Token Index: 954

Text #15

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1962. Min Act: -0.0000

Data Index: 282438 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1617450 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1930. Min Act: -0.0000

Data Index: 806821 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1259425 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1569160 (The Pile)

Max Activating Token Index: 170