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

Dataset: The Pile

Neuron 4883 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1595576 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1056390 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6465. Min Act: 0.0000

Data Index: 1028828 (The Pile)

Max Activating Token Index: 712

Text #3

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6327. Min Act: -0.0000

Data Index: 663091 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6166. Min Act: -0.0000

Data Index: 740560 (The Pile)

Max Activating Token Index: 36

Text #5

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1091858 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6090. Min Act: 0.0000

Data Index: 921626 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6324. Min Act: 0.0000

Data Index: 1009215 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6432. Min Act: -0.0000

Data Index: 377955 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1141610 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5952. Min Act: -0.0000

Data Index: 922741 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5754. Min Act: -0.0000

Data Index: 707421 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6009. Min Act: 0.0000

Data Index: 1680493 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5647. Min Act: -0.0000

Data Index: 720074 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1424474 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1994592 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5897. Min Act: -0.0000

Data Index: 682758 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1876329 (The Pile)

Max Activating Token Index: 877

Text #18

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5667. Min Act: -0.0000

Data Index: 927111 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1907436 (The Pile)

Max Activating Token Index: 500