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

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

Neuron 1613 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.6202. Min Act: -0.0005

Data Index: 1089639 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4895. Min Act: -0.0005

Data Index: 792751 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5680. Min Act: -0.0005

Data Index: 712019 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5286. Min Act: -0.0005

Data Index: 1092143 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5917. Min Act: -0.0005

Data Index: 838752 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5646. Min Act: -0.0005

Data Index: 365278 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5248. Min Act: -0.0005

Data Index: 210780 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5346. Min Act: -0.0005

Data Index: 322277 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5693. Min Act: -0.0005

Data Index: 732200 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4896. Min Act: -0.0005

Data Index: 759611 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5673. Min Act: -0.0005

Data Index: 566963 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5554. Min Act: -0.0005

Data Index: 692881 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4656. Min Act: -0.0005

Data Index: 787602 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4938. Min Act: -0.0005

Data Index: 383105 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.5195. Min Act: -0.0005

Data Index: 35395 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4732. Min Act: -0.0005

Data Index: 890239 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4257. Min Act: -0.0005

Data Index: 64183 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4430. Min Act: -0.0005

Data Index: 24813 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4798. Min Act: -0.0005

Data Index: 10451 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.6202. Min Range: -0.6202

Max Act: 0.4418. Min Act: -0.0005

Data Index: 374079 (C4 (Web Text))

Max Activating Token Index: 988