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

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

Neuron 3838 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5498. Min Act: -0.0002

Data Index: 387289 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5535. Min Act: -0.0002

Data Index: 645484 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5285. Min Act: -0.0002

Data Index: 270320 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5963. Min Act: -0.0002

Data Index: 417579 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4134. Min Act: -0.0002

Data Index: 776907 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5249. Min Act: -0.0002

Data Index: 828751 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4927. Min Act: -0.0002

Data Index: 1002889 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4652. Min Act: -0.0002

Data Index: 12641 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5068. Min Act: -0.0002

Data Index: 810863 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5079. Min Act: -0.0002

Data Index: 790228 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4873. Min Act: -0.0002

Data Index: 311120 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5353. Min Act: -0.0002

Data Index: 32061 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4640. Min Act: -0.0002

Data Index: 171816 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4790. Min Act: -0.0002

Data Index: 373593 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4888. Min Act: -0.0002

Data Index: 998101 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5247. Min Act: -0.0002

Data Index: 93219 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4677. Min Act: -0.0002

Data Index: 716350 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5052. Min Act: -0.0002

Data Index: 154049 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4860. Min Act: -0.0002

Data Index: 1163976 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5227. Min Act: -0.0002

Data Index: 370776 (C4 (Web Text))

Max Activating Token Index: 128