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

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

Neuron 4701 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1373. Min Act: -0.0002

Data Index: 653121 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1295. Min Act: -0.0002

Data Index: 18426 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1218. Min Act: -0.0002

Data Index: 755293 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1059. Min Act: -0.0002

Data Index: 153867 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0989. Min Act: -0.0002

Data Index: 672061 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1019. Min Act: -0.0002

Data Index: 16066 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0943. Min Act: -0.0002

Data Index: 587004 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1156251 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0976. Min Act: -0.0002

Data Index: 927318 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0962. Min Act: -0.0002

Data Index: 114606 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1002. Min Act: -0.0002

Data Index: 890563 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0958. Min Act: -0.0002

Data Index: 499679 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0950. Min Act: -0.0002

Data Index: 916032 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0946. Min Act: -0.0002

Data Index: 659434 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0946. Min Act: -0.0002

Data Index: 718423 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0948. Min Act: -0.0002

Data Index: 723382 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0942. Min Act: -0.0002

Data Index: 618290 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1162229 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0936. Min Act: -0.0002

Data Index: 756265 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0936. Min Act: -0.0002

Data Index: 486945 (C4 (Web Text))

Max Activating Token Index: 5