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

Dataset: The Pile

Neuron 1848 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1289934 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1011174 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.8641. Min Act: -0.0000

Data Index: 320697 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6381. Min Act: -0.0000

Data Index: 491392 (The Pile)

Max Activating Token Index: 303

Text #4

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1859675 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1636961 (The Pile)

Max Activating Token Index: 440

Text #6

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1584123 (The Pile)

Max Activating Token Index: 320

Text #7

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6786. Min Act: -0.0000

Data Index: 167055 (The Pile)

Max Activating Token Index: 313

Text #8

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6214. Min Act: -0.0000

Data Index: 273282 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.7010. Min Act: -0.0000

Data Index: 89172 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1031863 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1532392 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6655. Min Act: -0.0000

Data Index: 71102 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6700. Min Act: -0.0000

Data Index: 228380 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6744. Min Act: -0.0000

Data Index: 611788 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6780. Min Act: -0.0000

Data Index: 861721 (The Pile)

Max Activating Token Index: 700

Text #16

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6909. Min Act: -0.0000

Data Index: 129287 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1597630 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1300223 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1775704 (The Pile)

Max Activating Token Index: 860