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

Dataset: The Pile

Neuron 433 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1960. Min Range: -1.1960

Max Act: 1.1960. Min Act: -0.0000

Data Index: 877216 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 1.1960. Min Range: -1.1960

Max Act: 1.0054. Min Act: -0.0000

Data Index: 1725501 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1169861 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 1.1960. Min Range: -1.1960

Max Act: 1.0263. Min Act: -0.0000

Data Index: 197643 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9376. Min Act: -0.0000

Data Index: 545890 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1192510 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9557. Min Act: -0.0000

Data Index: 826905 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8707. Min Act: -0.0000

Data Index: 5558 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1236431 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1971918 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1785016 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1868669 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1217136 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.7902. Min Act: -0.0000

Data Index: 534991 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8519. Min Act: -0.0000

Data Index: 398324 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1600335 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.7883. Min Act: -0.0000

Data Index: 247669 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1802048 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.7951. Min Act: -0.0000

Data Index: 200608 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1500806 (The Pile)

Max Activating Token Index: 307