Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3764 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2859. Min Range: -2.2859

Max Act: 2.0150. Min Act: -0.0000

Data Index: 1125020 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 2.2859. Min Range: -2.2859

Max Act: 2.2859. Min Act: -0.0000

Data Index: 306735 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 2.2859. Min Range: -2.2859

Max Act: 2.0227. Min Act: -0.0000

Data Index: 498413 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.9353. Min Act: -0.0000

Data Index: 795984 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.9428. Min Act: -0.0000

Data Index: 199021 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.8711. Min Act: -0.0000

Data Index: 562665 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.7456. Min Act: -0.0000

Data Index: 177836 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.5599. Min Act: -0.0000

Data Index: 1252571 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.5525. Min Act: -0.0000

Data Index: 399703 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.6580. Min Act: -0.0000

Data Index: 449758 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.5413. Min Act: -0.0000

Data Index: 893753 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.5811. Min Act: -0.0000

Data Index: 762983 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.5057. Min Act: -0.0000

Data Index: 474378 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.5648. Min Act: 0.0000

Data Index: 689698 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.3808. Min Act: -0.0000

Data Index: 498351 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.4950. Min Act: -0.0000

Data Index: 823619 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.4977. Min Act: -0.0000

Data Index: 592366 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.4629. Min Act: -0.0000

Data Index: 648037 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.4518. Min Act: -0.0000

Data Index: 1001343 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 2.2859. Min Range: -2.2859

Max Act: 1.4406. Min Act: -0.0000

Data Index: 89385 (C4 (Web Text))

Max Activating Token Index: 51