Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 717 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2887. Min Act: -0.0003

Data Index: 447055 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2589. Min Act: -0.0003

Data Index: 1315880 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2573. Min Act: -0.0003

Data Index: 918117 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2918. Min Act: -0.0003

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2650. Min Act: -0.0003

Data Index: 203155 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2903. Min Act: -0.0003

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2735. Min Act: -0.0003

Data Index: 1064953 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2636. Min Act: -0.0003

Data Index: 34568 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2805. Min Act: -0.0003

Data Index: 173424 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2353. Min Act: -0.0003

Data Index: 884087 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2228. Min Act: -0.0003

Data Index: 278469 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2285. Min Act: -0.0003

Data Index: 1241528 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2194. Min Act: -0.0003

Data Index: 982035 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2410. Min Act: -0.0003

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2040. Min Act: -0.0003

Data Index: 942053 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1882. Min Act: -0.0003

Data Index: 758483 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2175. Min Act: -0.0003

Data Index: 149515 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2086. Min Act: -0.0003

Data Index: 837321 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2370. Min Act: -0.0003

Data Index: 1016779 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1961. Min Act: -0.0003

Data Index: 785341 (C4 (Web Text))

Max Activating Token Index: 91