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

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

Neuron 1391 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8946. Min Act: -0.0001

Data Index: 814718 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8984. Min Act: -0.0001

Data Index: 760221 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8899. Min Act: -0.0001

Data Index: 322288 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8395. Min Act: -0.0001

Data Index: 545796 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8247. Min Act: -0.0001

Data Index: 1133012 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8126. Min Act: -0.0001

Data Index: 601298 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8013. Min Act: -0.0001

Data Index: 620920 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7150. Min Act: -0.0001

Data Index: 627143 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7668. Min Act: -0.0001

Data Index: 900519 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7802. Min Act: -0.0001

Data Index: 431477 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7673. Min Act: -0.0001

Data Index: 664546 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8005. Min Act: -0.0001

Data Index: 738834 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7732. Min Act: -0.0001

Data Index: 988872 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7349. Min Act: -0.0001

Data Index: 988755 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7891. Min Act: -0.0001

Data Index: 899215 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7684. Min Act: -0.0001

Data Index: 484263 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7386. Min Act: -0.0001

Data Index: 1250802 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7823. Min Act: -0.0001

Data Index: 103809 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7545. Min Act: -0.0001

Data Index: 1108710 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7490. Min Act: -0.0001

Data Index: 138912 (C4 (Web Text))

Max Activating Token Index: 330