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

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

Neuron 3049 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1339199 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.5275. Min Act: -0.0000

Data Index: 849842 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4948. Min Act: -0.0000

Data Index: 494914 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.5234. Min Act: -0.0000

Data Index: 643594 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4843. Min Act: -0.0000

Data Index: 196380 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1331645 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4974. Min Act: -0.0000

Data Index: 557352 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4798. Min Act: -0.0000

Data Index: 333485 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4634. Min Act: -0.0000

Data Index: 433801 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4665. Min Act: -0.0000

Data Index: 111848 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1341821 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4432. Min Act: -0.0000

Data Index: 870821 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4705. Min Act: -0.0000

Data Index: 940483 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1061039 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4515. Min Act: -0.0000

Data Index: 500031 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1250201 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4286. Min Act: -0.0000

Data Index: 402165 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4129. Min Act: -0.0000

Data Index: 40732 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4280. Min Act: -0.0000

Data Index: 372645 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.5420. Min Range: -0.5420

Max Act: 0.4279. Min Act: -0.0000

Data Index: 985643 (C4 (Web Text))

Max Activating Token Index: 873