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

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

Neuron 3182 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: 0.3750. Min Range: -0.3750

Max Act: 0.3750. Min Act: -0.0000

Data Index: 346571 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3394. Min Act: -0.0000

Data Index: 256450 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2968. Min Act: -0.0000

Data Index: 214175 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2748. Min Act: -0.0000

Data Index: 118879 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2843. Min Act: -0.0001

Data Index: 1226287 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2822. Min Act: -0.0001

Data Index: 711079 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2925. Min Act: -0.0001

Data Index: 512552 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2850. Min Act: -0.0001

Data Index: 873800 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2797. Min Act: -0.0001

Data Index: 845943 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2881. Min Act: -0.0001

Data Index: 1096822 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2777. Min Act: -0.0000

Data Index: 842421 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1113864 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2707. Min Act: -0.0001

Data Index: 97112 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2771. Min Act: -0.0001

Data Index: 370976 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2589. Min Act: -0.0000

Data Index: 82195 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2866. Min Act: -0.0000

Data Index: 370585 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2650. Min Act: -0.0000

Data Index: 778185 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2538. Min Act: -0.0001

Data Index: 923502 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2617. Min Act: -0.0001

Data Index: 1253998 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2554. Min Act: -0.0001

Data Index: 152524 (C4 (Web Text))

Max Activating Token Index: 52