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

Dataset: The Pile

Neuron 760 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: 1.9308. Min Range: -1.9308

Max Act: 1.9308. Min Act: -0.0000

Data Index: 982889 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1417449 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.8161. Min Act: -0.0000

Data Index: 291617 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.7522. Min Act: -0.0000

Data Index: 1289613 (The Pile)

Max Activating Token Index: 672

Text #4

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.5521. Min Act: -0.0000

Data Index: 1637913 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.8156. Min Act: -0.0000

Data Index: 1133277 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.6755. Min Act: -0.0000

Data Index: 823703 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.6642. Min Act: -0.0000

Data Index: 674462 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.7156. Min Act: -0.0000

Data Index: 963275 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.7831. Min Act: -0.0000

Data Index: 620477 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.5629. Min Act: -0.0000

Data Index: 450584 (The Pile)

Max Activating Token Index: 462

Text #11

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.4199. Min Act: -0.0000

Data Index: 685243 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1073573 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.4962. Min Act: -0.0000

Data Index: 1697724 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.6376. Min Act: -0.0000

Data Index: 859386 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.4584. Min Act: -0.0000

Data Index: 939340 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.5145. Min Act: -0.0000

Data Index: 734656 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.4448. Min Act: -0.0000

Data Index: 566381 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.4398. Min Act: -0.0000

Data Index: 1107207 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 1.9308. Min Range: -1.9308

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1881934 (The Pile)

Max Activating Token Index: 729