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

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

Neuron 3959 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2602. Min Act: -0.0003

Data Index: 408905 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2232. Min Act: -0.0003

Data Index: 502969 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2145. Min Act: -0.0003

Data Index: 125729 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2114. Min Act: -0.0003

Data Index: 1250458 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2015. Min Act: -0.0003

Data Index: 1331679 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2010. Min Act: -0.0003

Data Index: 1033377 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1915. Min Act: -0.0002

Data Index: 700299 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1970. Min Act: -0.0003

Data Index: 864793 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2036. Min Act: -0.0003

Data Index: 848405 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1920. Min Act: -0.0003

Data Index: 528183 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1885. Min Act: -0.0003

Data Index: 380734 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1878. Min Act: -0.0002

Data Index: 1064824 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1758. Min Act: -0.0003

Data Index: 617677 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1816. Min Act: -0.0003

Data Index: 289236 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1797. Min Act: -0.0003

Data Index: 1188392 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1779. Min Act: -0.0003

Data Index: 531722 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1777. Min Act: -0.0003

Data Index: 701191 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1753. Min Act: -0.0003

Data Index: 714577 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1748. Min Act: -0.0002

Data Index: 582512 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1686. Min Act: -0.0003

Data Index: 1055786 (C4 (Web Text))

Max Activating Token Index: 320