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

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

Neuron 3510 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0661. Min Range: -2.0661

Max Act: 2.0661. Min Act: -0.0000

Data Index: 572252 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.8845. Min Act: -0.0000

Data Index: 240695 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.8660. Min Act: -0.0000

Data Index: 892216 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1293461 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.8152. Min Act: -0.0000

Data Index: 971781 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.6228. Min Act: -0.0000

Data Index: 355178 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.7098. Min Act: -0.0000

Data Index: 236015 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.7101. Min Act: -0.0000

Data Index: 863567 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5465. Min Act: -0.0000

Data Index: 153575 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5379. Min Act: -0.0000

Data Index: 264440 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5346. Min Act: -0.0000

Data Index: 292453 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5386. Min Act: -0.0000

Data Index: 552315 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.4874. Min Act: -0.0000

Data Index: 783426 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5203. Min Act: -0.0000

Data Index: 636248 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5084. Min Act: -0.0000

Data Index: 289672 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5186. Min Act: -0.0000

Data Index: 509263 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.4452. Min Act: -0.0000

Data Index: 1249835 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5211. Min Act: -0.0000

Data Index: 435525 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5016. Min Act: -0.0000

Data Index: 1286423 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.5474. Min Act: -0.0000

Data Index: 535760 (C4 (Web Text))

Max Activating Token Index: 322