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

Dataset: The Pile

Neuron 3366 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: 1.2739. Min Range: -1.2739

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1231169 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.2591. Min Act: -0.0000

Data Index: 460363 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1636. Min Act: -0.0000

Data Index: 1426002 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1583. Min Act: -0.0000

Data Index: 907457 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.2739. Min Act: -0.0000

Data Index: 1013912 (The Pile)

Max Activating Token Index: 150

Text #5

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1492. Min Act: -0.0000

Data Index: 226672 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1261003 (The Pile)

Max Activating Token Index: 593

Text #7

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1712053 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1923194 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1180614 (The Pile)

Max Activating Token Index: 268

Text #10

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1606129 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9880. Min Act: -0.0000

Data Index: 907300 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1212641 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9320. Min Act: 0.0000

Data Index: 1967693 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9907. Min Act: -0.0000

Data Index: 556498 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0173. Min Act: -0.0000

Data Index: 355585 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1932752 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0064. Min Act: -0.0000

Data Index: 712044 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1158818 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1800293 (The Pile)

Max Activating Token Index: 732