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

Dataset: The Pile

Neuron 335 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: 0.8178. Min Range: -0.8178

Max Act: 0.7934. Min Act: -0.0000

Data Index: 325819 (The Pile)

Max Activating Token Index: 707

Text #1

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1004427 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7917. Min Act: -0.0000

Data Index: 86446 (The Pile)

Max Activating Token Index: 580

Text #3

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1177689 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1642008 (The Pile)

Max Activating Token Index: 302

Text #5

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7333. Min Act: -0.0000

Data Index: 391210 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1137227 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1651431 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6827. Min Act: -0.0000

Data Index: 535267 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7124. Min Act: -0.0000

Data Index: 94775 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1030463 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1736240 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7695. Min Act: -0.0000

Data Index: 448130 (The Pile)

Max Activating Token Index: 652

Text #13

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1777820 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1328875 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6931. Min Act: -0.0000

Data Index: 903548 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1379672 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7163. Min Act: -0.0000

Data Index: 225483 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6914. Min Act: -0.0000

Data Index: 790505 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7139. Min Act: -0.0000

Data Index: 305142 (The Pile)

Max Activating Token Index: 263