Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5803 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2952. Min Act: -0.0000

Data Index: 279440 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2973. Min Act: 0.0001

Data Index: 426592 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.3067. Min Act: -0.0000

Data Index: 43453 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2912. Min Act: -0.0000

Data Index: 962865 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2686. Min Act: -0.0000

Data Index: 465240 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2894. Min Act: -0.0000

Data Index: 863009 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2750. Min Act: -0.0000

Data Index: 348798 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1355214 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2625. Min Act: -0.0000

Data Index: 594752 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2727. Min Act: -0.0000

Data Index: 369492 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2655. Min Act: -0.0000

Data Index: 357040 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1349720 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2536. Min Act: -0.0000

Data Index: 305017 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2605. Min Act: -0.0000

Data Index: 55232 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2511. Min Act: -0.0000

Data Index: 348062 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2365. Min Act: -0.0000

Data Index: 753971 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2447. Min Act: -0.0000

Data Index: 248556 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2469. Min Act: -0.0000

Data Index: 721759 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2505. Min Act: -0.0000

Data Index: 515934 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2443. Min Act: -0.0000

Data Index: 385264 (C4 (Web Text))

Max Activating Token Index: 670