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

Dataset: The Pile

Neuron 489 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: 1.1959. Min Range: -1.1959

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1772790 (The Pile)

Max Activating Token Index: 330

Text #1

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1859. Min Act: -0.0000

Data Index: 1238032 (The Pile)

Max Activating Token Index: 689

Text #2

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1621323 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.0979. Min Act: -0.0000

Data Index: 11635 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9332. Min Act: -0.0000

Data Index: 494925 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8805. Min Act: -0.0000

Data Index: 57544 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8665. Min Act: -0.0000

Data Index: 383230 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1595356 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1012719 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7985. Min Act: -0.0000

Data Index: 518003 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8101. Min Act: -0.0000

Data Index: 760454 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8098. Min Act: -0.0000

Data Index: 514629 (The Pile)

Max Activating Token Index: 778

Text #12

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7449. Min Act: -0.0000

Data Index: 292951 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8548. Min Act: -0.0000

Data Index: 267751 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7926. Min Act: -0.0000

Data Index: 768342 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1451874 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8237. Min Act: -0.0000

Data Index: 402911 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1787254 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1913714 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1416327 (The Pile)

Max Activating Token Index: 978