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

Dataset: The Pile

Neuron 3596 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: 0.7270. Min Range: -0.7270

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1353275 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1047870 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6693. Min Act: -0.0000

Data Index: 889783 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1418328 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6443. Min Act: -0.0000

Data Index: 362173 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6529. Min Act: -0.0000

Data Index: 931241 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5974. Min Act: -0.0000

Data Index: 382731 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5439. Min Act: -0.0000

Data Index: 943463 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5914. Min Act: -0.0000

Data Index: 524155 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1741459 (The Pile)

Max Activating Token Index: 716

Text #10

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5376. Min Act: -0.0000

Data Index: 328629 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5608. Min Act: -0.0000

Data Index: 419718 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5826. Min Act: -0.0000

Data Index: 415291 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1823617 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5497. Min Act: -0.0000

Data Index: 690894 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1826833 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1742790 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1811252 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1315372 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5261. Min Act: -0.0000

Data Index: 171647 (The Pile)

Max Activating Token Index: 380