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

Dataset: The Pile

Neuron 3936 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.8388. Min Act: -0.0000

Data Index: 572406 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.8919. Min Act: -0.0000

Data Index: 1457313 (The Pile)

Max Activating Token Index: 672

Text #2

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.7208. Min Act: -0.0000

Data Index: 1403533 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.6771. Min Act: -0.0000

Data Index: 1977760 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.8045. Min Act: -0.0000

Data Index: 414117 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5794. Min Act: -0.0000

Data Index: 1350065 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.7740. Min Act: -0.0000

Data Index: 629847 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.7180. Min Act: -0.0000

Data Index: 58039 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1716446 (The Pile)

Max Activating Token Index: 693

Text #9

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5521. Min Act: -0.0000

Data Index: 452003 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5291. Min Act: -0.0000

Data Index: 584495 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.4594. Min Act: -0.0000

Data Index: 706320 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.6055. Min Act: -0.0000

Data Index: 769082 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1881945 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.4099. Min Act: -0.0000

Data Index: 613246 (The Pile)

Max Activating Token Index: 310

Text #15

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.3706. Min Act: -0.0000

Data Index: 1343448 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1848196 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.4092. Min Act: -0.0000

Data Index: 772103 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.4476. Min Act: -0.0000

Data Index: 907499 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.3342. Min Act: -0.0000

Data Index: 745477 (The Pile)

Max Activating Token Index: 648