Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 987 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1281. Min Act: -0.0003

Data Index: 939448 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1128. Min Act: -0.0003

Data Index: 551616 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1073. Min Act: -0.0003

Data Index: 1081085 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1066. Min Act: -0.0003

Data Index: 1294652 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1116. Min Act: -0.0003

Data Index: 380720 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1060. Min Act: -0.0003

Data Index: 795891 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0973. Min Act: -0.0003

Data Index: 55486 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1120. Min Act: -0.0003

Data Index: 1008969 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0912. Min Act: -0.0003

Data Index: 927137 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1010. Min Act: -0.0003

Data Index: 1347897 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0967. Min Act: -0.0003

Data Index: 1304163 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0984. Min Act: -0.0003

Data Index: 215658 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0841. Min Act: -0.0003

Data Index: 364662 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0936. Min Act: -0.0003

Data Index: 825447 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0931. Min Act: -0.0003

Data Index: 1185131 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0966. Min Act: -0.0003

Data Index: 91015 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0888. Min Act: -0.0003

Data Index: 1276468 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0854. Min Act: -0.0003

Data Index: 453554 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0887. Min Act: -0.0003

Data Index: 387504 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0879. Min Act: -0.0003

Data Index: 683675 (C4 (Web Text))

Max Activating Token Index: 605