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

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

Neuron 4145 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.5664. Min Act: -0.0000

Data Index: 668904 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.5487. Min Act: -0.0000

Data Index: 799877 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1182449 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1168002 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4664. Min Act: -0.0000

Data Index: 372165 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4551. Min Act: -0.0000

Data Index: 815612 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4441. Min Act: -0.0000

Data Index: 861597 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4330. Min Act: -0.0000

Data Index: 69148 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4539. Min Act: -0.0000

Data Index: 56150 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1182133 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1067972 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4059. Min Act: -0.0000

Data Index: 246279 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1290856 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3761. Min Act: -0.0000

Data Index: 761920 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1238374 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1176666 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1043974 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3551. Min Act: -0.0000

Data Index: 558940 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1351395 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3671. Min Act: -0.0000

Data Index: 722769 (C4 (Web Text))

Max Activating Token Index: 400