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

Dataset: The Pile

Neuron 3727 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1613813 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1856234 (The Pile)

Max Activating Token Index: 93

Text #2

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5824. Min Act: -0.0000

Data Index: 535454 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1910209 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.6432. Min Act: -0.0000

Data Index: 221146 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1706512 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5492. Min Act: -0.0000

Data Index: 235416 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1141077 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5894. Min Act: -0.0000

Data Index: 271271 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1905469 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1513371 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5151. Min Act: -0.0000

Data Index: 73347 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5957. Min Act: -0.0000

Data Index: 391380 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1996771 (The Pile)

Max Activating Token Index: 95

Text #14

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1505666 (The Pile)

Max Activating Token Index: 96

Text #15

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5123. Min Act: -0.0000

Data Index: 106864 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5284. Min Act: -0.0000

Data Index: 377764 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5741. Min Act: -0.0000

Data Index: 553596 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1799928 (The Pile)

Max Activating Token Index: 164

Text #19

Max Range: 0.6432. Min Range: -0.6432

Max Act: 0.6000. Min Act: -0.0000

Data Index: 958837 (The Pile)

Max Activating Token Index: 136