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

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

Neuron 3031 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: 0.4772. Min Range: -0.4772

Max Act: 0.4643. Min Act: -0.0001

Data Index: 400368 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4772. Min Act: -0.0001

Data Index: 358620 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4321. Min Act: -0.0001

Data Index: 955085 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4006. Min Act: -0.0002

Data Index: 786737 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4052. Min Act: -0.0002

Data Index: 1284825 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4170. Min Act: -0.0002

Data Index: 158105 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4086. Min Act: -0.0002

Data Index: 190564 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4193. Min Act: -0.0001

Data Index: 784481 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3796. Min Act: -0.0002

Data Index: 462823 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4010. Min Act: -0.0001

Data Index: 629056 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3857. Min Act: -0.0002

Data Index: 90759 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3754. Min Act: -0.0002

Data Index: 501933 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3946. Min Act: -0.0001

Data Index: 29717 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3734. Min Act: -0.0001

Data Index: 77197 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3585. Min Act: -0.0001

Data Index: 942903 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3913. Min Act: -0.0001

Data Index: 756822 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3807. Min Act: -0.0002

Data Index: 1079871 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3793. Min Act: -0.0001

Data Index: 700086 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3736. Min Act: -0.0002

Data Index: 1085998 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3823. Min Act: -0.0002

Data Index: 995217 (C4 (Web Text))

Max Activating Token Index: 747