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

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

Neuron 5172 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1257821 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.0262. Min Range: -1.0262

Max Act: 1.0262. Min Act: -0.0000

Data Index: 909195 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1269738 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8834. Min Act: -0.0000

Data Index: 337159 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8229. Min Act: 0.0000

Data Index: 1098200 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1250637 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8244. Min Act: 0.0000

Data Index: 269364 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8176. Min Act: 0.0000

Data Index: 1135809 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8055. Min Act: 0.0000

Data Index: 871615 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7972. Min Act: 0.0000

Data Index: 746555 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7848. Min Act: -0.0000

Data Index: 411922 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1080358 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7618. Min Act: -0.0000

Data Index: 785011 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7192. Min Act: -0.0000

Data Index: 713681 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.6917. Min Act: -0.0000

Data Index: 584044 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7849. Min Act: -0.0000

Data Index: 257957 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7522. Min Act: -0.0000

Data Index: 923452 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8052. Min Act: -0.0000

Data Index: 333189 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1184995 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7701. Min Act: -0.0000

Data Index: 391277 (C4 (Web Text))

Max Activating Token Index: 752