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

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

Neuron 3693 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: 4.6823. Min Range: -4.6823

Max Act: 4.6823. Min Act: -0.0000

Data Index: 399467 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 4.6823. Min Range: -4.6823

Max Act: 3.6434. Min Act: -0.0000

Data Index: 616315 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 4.6823. Min Range: -4.6823

Max Act: 4.0185. Min Act: -0.0000

Data Index: 775288 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 4.6823. Min Range: -4.6823

Max Act: 3.5813. Min Act: -0.0000

Data Index: 805372 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 4.6823. Min Range: -4.6823

Max Act: 3.6333. Min Act: -0.0000

Data Index: 586659 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.8274. Min Act: -0.0000

Data Index: 50433 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.5267. Min Act: -0.0000

Data Index: 998115 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.3699. Min Act: -0.0000

Data Index: 558857 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.4937. Min Act: -0.0000

Data Index: 517459 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.3940. Min Act: -0.0000

Data Index: 936479 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.2909. Min Act: -0.0000

Data Index: 372194 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.4296. Min Act: -0.0000

Data Index: 1124674 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.1861. Min Act: -0.0000

Data Index: 857413 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.1095. Min Act: -0.0000

Data Index: 439266 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 4.6823. Min Range: -4.6823

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1083566 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.1496. Min Act: -0.0000

Data Index: 883007 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.3680. Min Act: -0.0000

Data Index: 1326739 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.3518. Min Act: -0.0000

Data Index: 879363 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 4.6823. Min Range: -4.6823

Max Act: 2.0416. Min Act: -0.0000

Data Index: 239723 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 4.6823. Min Range: -4.6823

Max Act: 1.9827. Min Act: -0.0000

Data Index: 643064 (C4 (Web Text))

Max Activating Token Index: 396