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

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

Neuron 2511 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.3793. Min Act: -0.0001

Data Index: 1183758 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.3645. Min Act: -0.0001

Data Index: 639115 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.3375. Min Act: -0.0001

Data Index: 157188 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1313599 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1355762 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2915. Min Act: -0.0001

Data Index: 1119927 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.3036. Min Act: -0.0001

Data Index: 1137217 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2946. Min Act: -0.0001

Data Index: 763147 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.3009. Min Act: -0.0001

Data Index: 410685 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2913. Min Act: -0.0001

Data Index: 1319830 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2613. Min Act: -0.0001

Data Index: 1238324 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2769. Min Act: -0.0001

Data Index: 387102 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2799. Min Act: -0.0001

Data Index: 595337 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2764. Min Act: -0.0001

Data Index: 244199 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2760. Min Act: -0.0001

Data Index: 494249 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2801. Min Act: -0.0001

Data Index: 809096 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2787. Min Act: -0.0001

Data Index: 1312932 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2609. Min Act: -0.0001

Data Index: 102104 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2792. Min Act: -0.0001

Data Index: 841341 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.3793. Min Range: -0.3793

Max Act: 0.2667. Min Act: -0.0001

Data Index: 108641 (C4 (Web Text))

Max Activating Token Index: 88