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

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

Neuron 3109 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4794. Min Act: -0.0000

Data Index: 691554 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4533. Min Act: -0.0000

Data Index: 726055 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3799. Min Act: -0.0000

Data Index: 137585 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3854. Min Act: -0.0000

Data Index: 664038 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3503. Min Act: -0.0000

Data Index: 967201 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3240. Min Act: -0.0000

Data Index: 940340 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3309. Min Act: -0.0000

Data Index: 431318 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3301. Min Act: -0.0000

Data Index: 184988 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3167. Min Act: -0.0000

Data Index: 43788 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2920. Min Act: -0.0000

Data Index: 229071 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2899. Min Act: -0.0000

Data Index: 499997 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2453. Min Act: -0.0000

Data Index: 538393 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2663. Min Act: -0.0000

Data Index: 339804 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1206555 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1152571 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2449. Min Act: -0.0000

Data Index: 563869 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1256908 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2761. Min Act: -0.0000

Data Index: 850140 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2454. Min Act: -0.0000

Data Index: 879378 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2648. Min Act: -0.0000

Data Index: 587651 (C4 (Web Text))

Max Activating Token Index: 174