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

Dataset: The Pile

Neuron 321 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.8027. Min Act: -0.0000

Data Index: 298255 (The Pile)

Max Activating Token Index: 934

Text #1

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7499. Min Act: -0.0000

Data Index: 953829 (The Pile)

Max Activating Token Index: 2

Text #2

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7447. Min Act: -0.0000

Data Index: 131785 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7349. Min Act: -0.0000

Data Index: 766849 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7376. Min Act: -0.0000

Data Index: 566409 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7261. Min Act: -0.0000

Data Index: 310300 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1434040 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1957194 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1221372 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1986460 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7179. Min Act: -0.0000

Data Index: 712368 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1067410 (The Pile)

Max Activating Token Index: 315

Text #12

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7101. Min Act: -0.0000

Data Index: 272311 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6905. Min Act: -0.0000

Data Index: 318542 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1985256 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1418417 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6895. Min Act: -0.0000

Data Index: 434061 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1117731 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1127656 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6534. Min Act: -0.0000

Data Index: 578278 (The Pile)

Max Activating Token Index: 275