Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 534 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1177. Min Act: -0.0002

Data Index: 653138 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1143. Min Act: -0.0002

Data Index: 76563 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1020. Min Act: -0.0002

Data Index: 1126723 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1299467 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0999. Min Act: -0.0002

Data Index: 781651 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1078. Min Act: -0.0002

Data Index: 532979 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1036. Min Act: -0.0002

Data Index: 70522 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0996. Min Act: -0.0002

Data Index: 327787 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1030. Min Act: -0.0002

Data Index: 753171 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1050. Min Act: -0.0002

Data Index: 304378 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0998. Min Act: -0.0002

Data Index: 569159 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1036. Min Act: -0.0002

Data Index: 628577 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1000. Min Act: -0.0002

Data Index: 380439 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1002. Min Act: -0.0002

Data Index: 806474 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0959. Min Act: -0.0002

Data Index: 444512 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1016. Min Act: -0.0002

Data Index: 904173 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0979. Min Act: -0.0002

Data Index: 996135 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0970. Min Act: -0.0002

Data Index: 393440 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0963. Min Act: -0.0002

Data Index: 899041 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1099742 (C4 (Web Text))

Max Activating Token Index: 550