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

Dataset: The Pile

Neuron 4845 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: 1.8142. Min Range: -1.8142

Max Act: 1.8142. Min Act: -0.0000

Data Index: 1057566 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.7598. Min Act: -0.0000

Data Index: 1933421 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.4016. Min Act: -0.0000

Data Index: 1542212 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.5872. Min Act: -0.0000

Data Index: 659917 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.4812. Min Act: -0.0000

Data Index: 1688339 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.3846. Min Act: -0.0000

Data Index: 527287 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.5526. Min Act: -0.0000

Data Index: 1546260 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.5406. Min Act: -0.0000

Data Index: 526133 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1426935 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.2682. Min Act: -0.0000

Data Index: 38943 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1019519 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.4858. Min Act: -0.0000

Data Index: 1186841 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.3105. Min Act: -0.0000

Data Index: 13979 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.4812. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.4638. Min Act: -0.0000

Data Index: 176222 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.3687. Min Act: -0.0000

Data Index: 1996202 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.4503. Min Act: -0.0000

Data Index: 858860 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.3745. Min Act: -0.0000

Data Index: 894172 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.3754. Min Act: -0.0000

Data Index: 226960 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 1.8142. Min Range: -1.8142

Max Act: 1.3820. Min Act: -0.0000

Data Index: 744958 (The Pile)

Max Activating Token Index: 810