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

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

Neuron 2244 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: 1.2462. Min Range: -1.2462

Max Act: 1.2462. Min Act: -0.0001

Data Index: 1238317 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.2105. Min Act: -0.0001

Data Index: 702927 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.1875. Min Act: -0.0001

Data Index: 1336764 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.1803. Min Act: -0.0001

Data Index: 564378 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.1780. Min Act: -0.0001

Data Index: 1257810 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.1061. Min Act: -0.0001

Data Index: 251171 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.1384. Min Act: -0.0001

Data Index: 293733 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.1364. Min Act: -0.0001

Data Index: 279863 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0931. Min Act: -0.0001

Data Index: 206377 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.1282. Min Act: -0.0001

Data Index: 840085 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0873. Min Act: -0.0001

Data Index: 158469 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0905. Min Act: -0.0001

Data Index: 1084213 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.1241. Min Act: -0.0001

Data Index: 135317 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0845. Min Act: -0.0001

Data Index: 1097610 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0635. Min Act: -0.0001

Data Index: 725463 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.1098. Min Act: -0.0001

Data Index: 1201841 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0464. Min Act: -0.0001

Data Index: 1253913 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0097. Min Act: -0.0001

Data Index: 320615 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0667. Min Act: -0.0001

Data Index: 558540 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0636. Min Act: -0.0001

Data Index: 923726 (C4 (Web Text))

Max Activating Token Index: 687