Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1550 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0003

Data Index: 747658 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0842. Min Act: -0.0003

Data Index: 425940 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0759. Min Act: -0.0003

Data Index: 117285 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0732. Min Act: -0.0003

Data Index: 300295 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0680. Min Act: -0.0003

Data Index: 483146 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1140430 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0697. Min Act: -0.0003

Data Index: 846996 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0705. Min Act: -0.0003

Data Index: 1271981 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0709. Min Act: -0.0004

Data Index: 983595 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0703. Min Act: -0.0004

Data Index: 738240 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1126134 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0699. Min Act: -0.0003

Data Index: 293317 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0723. Min Act: -0.0003

Data Index: 444333 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0716. Min Act: -0.0003

Data Index: 764979 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0688. Min Act: -0.0003

Data Index: 748081 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0686. Min Act: -0.0003

Data Index: 176974 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0688. Min Act: -0.0004

Data Index: 533950 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0681. Min Act: -0.0003

Data Index: 889002 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0669. Min Act: -0.0003

Data Index: 653766 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0665. Min Act: -0.0003

Data Index: 668552 (C4 (Web Text))

Max Activating Token Index: 335