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

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

Neuron 3866 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1251530 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1118747 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1190866 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.1254. Min Act: -0.0000

Data Index: 91025 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0705. Min Act: -0.0000

Data Index: 734863 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9584. Min Act: -0.0000

Data Index: 301429 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.1230. Min Act: -0.0000

Data Index: 34286 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9852. Min Act: -0.0000

Data Index: 168263 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1076252 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0025. Min Act: -0.0000

Data Index: 679294 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9850. Min Act: -0.0000

Data Index: 835651 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0004. Min Act: -0.0000

Data Index: 125736 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9728. Min Act: -0.0000

Data Index: 109423 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1068153 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9635. Min Act: -0.0000

Data Index: 219431 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1350536 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9106. Min Act: -0.0000

Data Index: 133378 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1104774 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.8928. Min Act: -0.0000

Data Index: 329940 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9073. Min Act: -0.0000

Data Index: 45822 (C4 (Web Text))

Max Activating Token Index: 706