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

Dataset: The Pile

Neuron 1868 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: 3.5497. Min Range: -3.5497

Max Act: 3.5066. Min Act: -0.0000

Data Index: 1766306 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.4070. Min Act: -0.0000

Data Index: 1087626 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.4707. Min Act: -0.0000

Data Index: 1026948 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.5497. Min Act: -0.0000

Data Index: 1372814 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.1997. Min Act: -0.0000

Data Index: 220289 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3193. Min Act: -0.0000

Data Index: 1880615 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3006. Min Act: -0.0000

Data Index: 268131 (The Pile)

Max Activating Token Index: 746

Text #7

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.1673. Min Act: -0.0000

Data Index: 120629 (The Pile)

Max Activating Token Index: 493

Text #8

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.2639. Min Act: -0.0000

Data Index: 1464279 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.0807. Min Act: -0.0000

Data Index: 1307991 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.1536. Min Act: -0.0000

Data Index: 600836 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.1103. Min Act: -0.0000

Data Index: 1331947 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.2157. Min Act: -0.0000

Data Index: 1930600 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.0560. Min Act: -0.0000

Data Index: 952524 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 3.5497. Min Range: -3.5497

Max Act: 2.8698. Min Act: -0.0000

Data Index: 351154 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 3.5497. Min Range: -3.5497

Max Act: 2.8784. Min Act: -0.0000

Data Index: 1186650 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.0314. Min Act: -0.0000

Data Index: 1913693 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.0031. Min Act: -0.0000

Data Index: 315393 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 3.5497. Min Range: -3.5497

Max Act: 2.9918. Min Act: -0.0000

Data Index: 1843865 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.0172. Min Act: -0.0000

Data Index: 129455 (The Pile)

Max Activating Token Index: 981