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

Dataset: The Pile

Neuron 2479 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.1781. Min Act: -0.0000

Data Index: 204674 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.2046. Min Act: -0.0000

Data Index: 509250 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1801470 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1218805 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.9364. Min Act: -0.0000

Data Index: 30082 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1185595 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1012837 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8022. Min Act: -0.0000

Data Index: 270783 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8112. Min Act: -0.0000

Data Index: 984973 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7503. Min Act: -0.0000

Data Index: 85324 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1765753 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1477140 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1891098 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1962105 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7592. Min Act: -0.0000

Data Index: 245603 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1152277 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.6992. Min Act: -0.0000

Data Index: 664982 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1874360 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.6711. Min Act: -0.0000

Data Index: 479076 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7273. Min Act: 0.0000

Data Index: 971805 (The Pile)

Max Activating Token Index: 866