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

Dataset: The Pile

Neuron 4415 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3670. Min Act: -0.0000

Data Index: 274153 (The Pile)

Max Activating Token Index: 106

Text #1

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2394. Min Act: -0.0000

Data Index: 985239 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.4568. Min Act: -0.0000

Data Index: 1033602 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1440737 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1117329 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1962. Min Act: -0.0000

Data Index: 958230 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0707. Min Act: -0.0000

Data Index: 180312 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0065. Min Act: 0.0001

Data Index: 1775633 (The Pile)

Max Activating Token Index: 451

Text #8

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0665. Min Act: -0.0000

Data Index: 22045 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1927163 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1237377 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1865957 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0605. Min Act: -0.0000

Data Index: 454202 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1453958 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1453079 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1730437 (The Pile)

Max Activating Token Index: 822

Text #16

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0264. Min Act: -0.0000

Data Index: 363952 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1820919 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1644574 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1955754 (The Pile)

Max Activating Token Index: 575