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

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

Neuron 3712 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.2089. Min Act: -0.0000

Data Index: 1282662 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.4368. Min Act: -0.0000

Data Index: 837369 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.2695. Min Act: -0.0000

Data Index: 635967 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.2125. Min Act: -0.0000

Data Index: 519504 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.2595. Min Act: -0.0000

Data Index: 804721 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.1270. Min Act: -0.0000

Data Index: 18474 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.1245. Min Act: -0.0000

Data Index: 1279076 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.3035. Min Act: -0.0000

Data Index: 814325 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.1571. Min Act: -0.0000

Data Index: 964743 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.3043. Min Act: -0.0000

Data Index: 861200 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.1037. Min Act: -0.0000

Data Index: 435707 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.2778. Min Act: -0.0000

Data Index: 840863 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 2.4368. Min Range: -2.4368

Max Act: 1.9168. Min Act: -0.0000

Data Index: 912178 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.0325. Min Act: -0.0000

Data Index: 951337 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 2.4368. Min Range: -2.4368

Max Act: 1.9050. Min Act: -0.0000

Data Index: 130856 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 2.4368. Min Range: -2.4368

Max Act: 1.8521. Min Act: -0.0000

Data Index: 273202 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 2.4368. Min Range: -2.4368

Max Act: 1.8623. Min Act: -0.0000

Data Index: 817579 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 2.4368. Min Range: -2.4368

Max Act: 2.1666. Min Act: -0.0000

Data Index: 874661 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 2.4368. Min Range: -2.4368

Max Act: 1.8086. Min Act: -0.0000

Data Index: 463862 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 2.4368. Min Range: -2.4368

Max Act: 1.9026. Min Act: -0.0000

Data Index: 748084 (C4 (Web Text))

Max Activating Token Index: 65