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

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

Neuron 3306 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: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0003

Data Index: 1042938 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0946. Min Act: -0.0002

Data Index: 49243 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0874. Min Act: -0.0003

Data Index: 1158145 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0881. Min Act: -0.0003

Data Index: 458420 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0816. Min Act: -0.0003

Data Index: 742269 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1105890 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0842. Min Act: -0.0003

Data Index: 547788 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0802. Min Act: -0.0002

Data Index: 656965 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0797. Min Act: -0.0003

Data Index: 40606 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0794. Min Act: -0.0003

Data Index: 169366 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0820. Min Act: -0.0002

Data Index: 344257 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0752. Min Act: -0.0003

Data Index: 752471 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0775. Min Act: -0.0003

Data Index: 60579 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0774. Min Act: -0.0003

Data Index: 295967 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0771. Min Act: -0.0003

Data Index: 856296 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0769. Min Act: -0.0003

Data Index: 1178027 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0765. Min Act: -0.0003

Data Index: 791679 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0757. Min Act: -0.0003

Data Index: 938116 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1106588 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0754. Min Act: -0.0003

Data Index: 999611 (C4 (Web Text))

Max Activating Token Index: 15