Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1581 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0005

Data Index: 77348 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0108. Min Act: -0.0004

Data Index: 1472588 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0100. Min Act: -0.0005

Data Index: 1649156 (Python Code)

Max Activating Token Index: 716

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0098. Min Act: -0.0005

Data Index: 701787 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0093. Min Act: -0.0005

Data Index: 87470 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1342431 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0090. Min Act: -0.0005

Data Index: 672337 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0089. Min Act: -0.0005

Data Index: 636958 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0090. Min Act: -0.0006

Data Index: 406878 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0090. Min Act: -0.0005

Data Index: 148284 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0088. Min Act: -0.0006

Data Index: 763978 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0089. Min Act: -0.0005

Data Index: 778101 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1150403 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0088. Min Act: -0.0005

Data Index: 1578664 (Python Code)

Max Activating Token Index: 803

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0086. Min Act: -0.0005

Data Index: 327174 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0086. Min Act: -0.0006

Data Index: 672961 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1400780 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0085. Min Act: -0.0005

Data Index: 163357 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0085. Min Act: -0.0005

Data Index: 851314 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0084. Min Act: -0.0005

Data Index: 1049470 (C4 (Web Text))

Max Activating Token Index: 369