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

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

Neuron 1592 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2697. Min Act: -0.0000

Data Index: 549808 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.3080. Min Act: -0.0000

Data Index: 942864 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2971. Min Act: -0.0000

Data Index: 596061 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2812. Min Act: -0.0000

Data Index: 804555 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1315998 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2821. Min Act: -0.0000

Data Index: 854681 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2985. Min Act: -0.0000

Data Index: 534437 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1229057 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2726. Min Act: -0.0000

Data Index: 735612 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2636. Min Act: -0.0000

Data Index: 324899 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2937. Min Act: -0.0000

Data Index: 916179 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2561. Min Act: -0.0000

Data Index: 244900 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2605. Min Act: -0.0000

Data Index: 598832 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2626. Min Act: -0.0000

Data Index: 757291 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1199427 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1100080 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1348858 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1033614 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2655. Min Act: -0.0000

Data Index: 942655 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2661. Min Act: -0.0000

Data Index: 335337 (C4 (Web Text))

Max Activating Token Index: 816