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

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

Neuron 5042 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.8763. Min Act: -0.0000

Data Index: 521841 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.9074. Min Act: -0.0000

Data Index: 147982 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.7362. Min Act: -0.0000

Data Index: 55893 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.7862. Min Act: -0.0000

Data Index: 417067 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.8111. Min Act: -0.0000

Data Index: 126390 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.6714. Min Act: -0.0000

Data Index: 985472 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.7127. Min Act: -0.0000

Data Index: 6675 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.6182. Min Act: -0.0000

Data Index: 607713 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.6475. Min Act: -0.0000

Data Index: 168067 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.6797. Min Act: -0.0000

Data Index: 485302 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.7009. Min Act: -0.0000

Data Index: 375152 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.6184. Min Act: -0.0000

Data Index: 932547 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.6481. Min Act: -0.0000

Data Index: 35559 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1228708 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1008973 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.5332. Min Act: -0.0000

Data Index: 76400 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.5166. Min Act: -0.0000

Data Index: 78909 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.5530. Min Act: -0.0000

Data Index: 492265 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1278988 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.9074. Min Range: -0.9074

Max Act: 0.5184. Min Act: -0.0000

Data Index: 642213 (C4 (Web Text))

Max Activating Token Index: 271