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

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

Neuron 2040 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1698. Min Range: -6.1698

Max Act: 6.1698. Min Act: -0.0000

Data Index: 1214790 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.8720. Min Act: -0.0000

Data Index: 993246 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6380. Min Act: -0.0000

Data Index: 638491 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.5955. Min Act: -0.0000

Data Index: 1129592 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.9650. Min Act: -0.0000

Data Index: 1163800 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.5227. Min Act: -0.0000

Data Index: 524105 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6828. Min Act: -0.0000

Data Index: 628135 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.4821. Min Act: -0.0000

Data Index: 934147 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6591. Min Act: -0.0000

Data Index: 592281 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6422. Min Act: -0.0000

Data Index: 220917 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.4804. Min Act: -0.0000

Data Index: 683873 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6603. Min Act: -0.0000

Data Index: 623321 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.8550. Min Act: -0.0000

Data Index: 1241461 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6357. Min Act: -0.0000

Data Index: 79265 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6486. Min Act: -0.0000

Data Index: 874506 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.8468. Min Act: -0.0000

Data Index: 661735 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.8474. Min Act: -0.0000

Data Index: 1237110 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6329. Min Act: -0.0000

Data Index: 901347 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6290. Min Act: -0.0000

Data Index: 247795 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 6.1698. Min Range: -6.1698

Max Act: 5.6216. Min Act: -0.0000

Data Index: 652572 (C4 (Web Text))

Max Activating Token Index: 386