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

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

Neuron 459 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: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0002

Data Index: 921343 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1037969 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1151848 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0749. Min Act: -0.0002

Data Index: 85242 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0771. Min Act: -0.0002

Data Index: 629780 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0744. Min Act: -0.0002

Data Index: 496462 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0709. Min Act: -0.0002

Data Index: 378444 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1098675 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0728. Min Act: -0.0002

Data Index: 203393 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1030660 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0665. Min Act: -0.0002

Data Index: 70530 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1275361 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0709. Min Act: -0.0002

Data Index: 103252 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0693. Min Act: -0.0002

Data Index: 364605 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1282349 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0691. Min Act: -0.0002

Data Index: 861249 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1124509 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0671. Min Act: -0.0002

Data Index: 975836 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1236686 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0695. Min Act: -0.0002

Data Index: 535525 (C4 (Web Text))

Max Activating Token Index: 781