Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4930 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2509. Min Act: -0.0001

Data Index: 260889 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2245. Min Act: -0.0001

Data Index: 393734 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1941. Min Act: -0.0001

Data Index: 860345 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1161176 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1920. Min Act: -0.0000

Data Index: 552309 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1953. Min Act: -0.0001

Data Index: 359402 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1895. Min Act: -0.0000

Data Index: 813072 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2219. Min Act: -0.0001

Data Index: 50404 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2144. Min Act: -0.0001

Data Index: 578341 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1986. Min Act: -0.0001

Data Index: 375836 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1061680 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1964. Min Act: -0.0001

Data Index: 84892 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1864. Min Act: -0.0001

Data Index: 61982 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1912. Min Act: -0.0001

Data Index: 820754 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1921. Min Act: -0.0001

Data Index: 577730 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1766. Min Act: -0.0001

Data Index: 249313 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1842. Min Act: -0.0001

Data Index: 439989 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1809. Min Act: -0.0001

Data Index: 70539 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1201066 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1706. Min Act: -0.0001

Data Index: 284416 (C4 (Web Text))

Max Activating Token Index: 588