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

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

Neuron 1897 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: 0.1125. Min Range: -0.1125

Max Act: 0.1115. Min Act: -0.0003

Data Index: 633897 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1027. Min Act: -0.0003

Data Index: 348476 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1125. Min Act: -0.0003

Data Index: 434064 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0995. Min Act: -0.0003

Data Index: 149865 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1027. Min Act: -0.0003

Data Index: 1104222 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0958. Min Act: -0.0003

Data Index: 42627 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1085687 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0912. Min Act: -0.0003

Data Index: 980311 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0850. Min Act: -0.0003

Data Index: 489037 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0929. Min Act: -0.0003

Data Index: 451086 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0819. Min Act: -0.0003

Data Index: 568781 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0876. Min Act: -0.0003

Data Index: 649654 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0838. Min Act: -0.0003

Data Index: 959452 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0842. Min Act: -0.0003

Data Index: 1161556 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0863. Min Act: -0.0003

Data Index: 822932 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0859. Min Act: -0.0003

Data Index: 805241 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0854. Min Act: -0.0003

Data Index: 733620 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0887. Min Act: -0.0003

Data Index: 1069232 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0838. Min Act: -0.0003

Data Index: 15147 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0867. Min Act: -0.0003

Data Index: 1300580 (C4 (Web Text))

Max Activating Token Index: 503