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

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

Neuron 2395 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1113873 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1056. Min Act: -0.0000

Data Index: 283383 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1030. Min Act: -0.0000

Data Index: 687028 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1029. Min Act: -0.0000

Data Index: 845995 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0946. Min Act: -0.0000

Data Index: 81863 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1215095 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0985. Min Act: -0.0000

Data Index: 849735 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1006. Min Act: -0.0000

Data Index: 386973 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1155992 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0906. Min Act: -0.0000

Data Index: 921861 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0853. Min Act: -0.0000

Data Index: 950545 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1154521 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0867. Min Act: -0.0000

Data Index: 919468 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0918. Min Act: -0.0000

Data Index: 711444 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0934. Min Act: -0.0000

Data Index: 215518 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0912. Min Act: -0.0000

Data Index: 964317 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1102727 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1264167 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1079246 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0832. Min Act: -0.0000

Data Index: 340234 (C4 (Web Text))

Max Activating Token Index: 271