Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2367 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0059. Min Act: -0.0003

Data Index: 545115 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1006937 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0003

Data Index: 411924 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1297635 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0003

Data Index: 586059 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0003

Data Index: 969854 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1183927 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0003

Data Index: 863631 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1032597 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0003

Data Index: 799203 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 415066 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 291634 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1135473 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 136523 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 76209 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 272995 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 519385 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0003

Data Index: 179568 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0003

Data Index: 837298 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 990274 (C4 (Web Text))

Max Activating Token Index: 215