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

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

Neuron 1535 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1240. Min Act: -0.0001

Data Index: 96251 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1165. Min Act: -0.0001

Data Index: 725409 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0910. Min Act: -0.0001

Data Index: 139348 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0863. Min Act: -0.0001

Data Index: 185499 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0690. Min Act: -0.0001

Data Index: 442628 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0835. Min Act: -0.0001

Data Index: 63737 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1311755 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0804. Min Act: -0.0001

Data Index: 316807 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0801. Min Act: -0.0001

Data Index: 704922 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0706. Min Act: -0.0001

Data Index: 49297 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1246925 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1094067 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0804. Min Act: -0.0001

Data Index: 834767 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0742. Min Act: -0.0001

Data Index: 414035 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0715. Min Act: -0.0000

Data Index: 983058 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0760. Min Act: -0.0001

Data Index: 893452 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0689. Min Act: -0.0001

Data Index: 377647 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0699. Min Act: -0.0000

Data Index: 1049339 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1341303 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0745. Min Act: -0.0000

Data Index: 991179 (C4 (Web Text))

Max Activating Token Index: 351