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

Dataset: The Pile

Neuron 3917 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: 0.8551. Min Range: -0.8551

Max Act: 0.8283. Min Act: -0.0000

Data Index: 173541 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1740214 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1200968 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1454217 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1431446 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.7399. Min Act: -0.0000

Data Index: 235869 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6844. Min Act: -0.0000

Data Index: 442773 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6172. Min Act: -0.0000

Data Index: 220298 (The Pile)

Max Activating Token Index: 246

Text #8

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6837. Min Act: -0.0000

Data Index: 357931 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5032. Min Act: -0.0000

Data Index: 860575 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5365. Min Act: -0.0000

Data Index: 228275 (The Pile)

Max Activating Token Index: 75

Text #11

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1699954 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5943. Min Act: -0.0000

Data Index: 584211 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1051324 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1357706 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1456427 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4426. Min Act: -0.0000

Data Index: 790987 (The Pile)

Max Activating Token Index: 166

Text #17

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4678. Min Act: -0.0000

Data Index: 525175 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4601. Min Act: -0.0000

Data Index: 186811 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4204. Min Act: -0.0000

Data Index: 515660 (The Pile)

Max Activating Token Index: 344