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

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

Neuron 4943 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: 0.1122. Min Range: -0.1122

Max Act: 0.1016. Min Act: -0.0002

Data Index: 635574 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1043. Min Act: -0.0002

Data Index: 408776 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0954. Min Act: -0.0002

Data Index: 462964 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0913. Min Act: -0.0002

Data Index: 767900 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1058395 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1059860 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1122. Min Act: -0.0002

Data Index: 845109 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0948. Min Act: -0.0002

Data Index: 249656 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0942. Min Act: -0.0002

Data Index: 379337 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0849. Min Act: -0.0002

Data Index: 335788 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0982. Min Act: -0.0002

Data Index: 798847 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1061015 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0958. Min Act: -0.0002

Data Index: 5755 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1324032 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0976. Min Act: -0.0002

Data Index: 346331 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0869. Min Act: -0.0002

Data Index: 564854 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0951. Min Act: -0.0002

Data Index: 120205 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0878. Min Act: -0.0002

Data Index: 18614 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0843. Min Act: -0.0002

Data Index: 585886 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1346416 (C4 (Web Text))

Max Activating Token Index: 166