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

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

Neuron 3370 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1148. Min Act: -0.0001

Data Index: 43626 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1012801 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1542443 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1038. Min Act: -0.0001

Data Index: 728518 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1013. Min Act: -0.0002

Data Index: 296307 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1050. Min Act: -0.0001

Data Index: 458476 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0978. Min Act: -0.0002

Data Index: 926317 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0960. Min Act: -0.0002

Data Index: 63188 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0967. Min Act: -0.0001

Data Index: 782355 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0926. Min Act: -0.0001

Data Index: 69603 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0852. Min Act: -0.0001

Data Index: 185547 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0946. Min Act: -0.0001

Data Index: 497305 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0889. Min Act: -0.0001

Data Index: 688672 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1213938 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0854. Min Act: -0.0001

Data Index: 36203 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1367350 (Python Code)

Max Activating Token Index: 632

Text #16

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0851. Min Act: -0.0001

Data Index: 568082 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0874. Min Act: -0.0002

Data Index: 742107 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0879. Min Act: -0.0002

Data Index: 297723 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0840. Min Act: -0.0001

Data Index: 916629 (C4 (Web Text))

Max Activating Token Index: 66