Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3258 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1248012 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1008. Min Act: -0.0001

Data Index: 783858 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0982. Min Act: -0.0001

Data Index: 612498 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1170216 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0967. Min Act: -0.0001

Data Index: 318489 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1337201 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1358529 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1628924 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1387724 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1502091 (Python Code)

Max Activating Token Index: 402

Text #10

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1178731 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0780. Min Act: -0.0001

Data Index: 877243 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1391179 (Python Code)

Max Activating Token Index: 571

Text #13

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0830. Min Act: -0.0001

Data Index: 475931 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0803. Min Act: -0.0001

Data Index: 353901 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0793. Min Act: -0.0001

Data Index: 840234 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0762. Min Act: -0.0001

Data Index: 516305 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1475117 (Python Code)

Max Activating Token Index: 392

Text #18

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0746. Min Act: -0.0001

Data Index: 674891 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1474226 (Python Code)

Max Activating Token Index: 382