Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 363 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1045106 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1328795 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0860. Min Act: -0.0002

Data Index: 858309 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1314737 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0880. Min Act: -0.0002

Data Index: 433445 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1064645 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1075720 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0797. Min Act: -0.0002

Data Index: 750346 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0753. Min Act: -0.0002

Data Index: 342457 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0745. Min Act: -0.0002

Data Index: 251015 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0762. Min Act: -0.0002

Data Index: 451863 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1099935 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0726. Min Act: -0.0002

Data Index: 441074 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1067315 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1294531 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1254243 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0739. Min Act: -0.0002

Data Index: 611058 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0706. Min Act: -0.0002

Data Index: 945885 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0724. Min Act: -0.0001

Data Index: 125113 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0710. Min Act: -0.0002

Data Index: 747333 (C4 (Web Text))

Max Activating Token Index: 242