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

Dataset: The Pile

Neuron 2532 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: 1.4912. Min Range: -1.4912

Max Act: 1.4912. Min Act: -0.0000

Data Index: 1551674 (The Pile)

Max Activating Token Index: 357

Text #1

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.2587. Min Act: -0.0000

Data Index: 1587438 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.1102. Min Act: -0.0000

Data Index: 861794 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.0681. Min Act: -0.0000

Data Index: 540454 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1457848 (The Pile)

Max Activating Token Index: 483

Text #5

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1251203 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1322731 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.0172. Min Act: -0.0000

Data Index: 1808314 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9641. Min Act: -0.0000

Data Index: 588503 (The Pile)

Max Activating Token Index: 769

Text #9

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9353. Min Act: -0.0000

Data Index: 204566 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9498. Min Act: -0.0000

Data Index: 954757 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1057376 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9331. Min Act: -0.0000

Data Index: 326958 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9525. Min Act: -0.0000

Data Index: 387714 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9373. Min Act: -0.0000

Data Index: 578130 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1762373 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.9000. Min Act: -0.0000

Data Index: 309985 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.8794. Min Act: -0.0000

Data Index: 435459 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.8230. Min Act: -0.0000

Data Index: 443415 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 1.4912. Min Range: -1.4912

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1067325 (The Pile)

Max Activating Token Index: 793