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

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

Neuron 2693 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4455. Min Range: -5.4455

Max Act: 5.3910. Min Act: -0.0000

Data Index: 564641 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 5.4455. Min Range: -5.4455

Max Act: 5.4455. Min Act: -0.0000

Data Index: 380553 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 5.4455. Min Range: -5.4455

Max Act: 5.4361. Min Act: -0.0000

Data Index: 507549 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 5.4455. Min Range: -5.4455

Max Act: 5.0522. Min Act: -0.0000

Data Index: 728619 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 5.4455. Min Range: -5.4455

Max Act: 5.3750. Min Act: -0.0000

Data Index: 1066089 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.9484. Min Act: -0.0000

Data Index: 727728 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.7719. Min Act: -0.0000

Data Index: 661529 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.7099. Min Act: -0.0000

Data Index: 1299143 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.9317. Min Act: -0.0001

Data Index: 1565046 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.3227. Min Act: -0.0000

Data Index: 1174481 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.5601. Min Act: -0.0001

Data Index: 1024036 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.3296. Min Act: -0.0000

Data Index: 41821 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.4792. Min Act: -0.0000

Data Index: 940887 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.6696. Min Act: -0.0000

Data Index: 913997 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.2105. Min Act: -0.0000

Data Index: 1264572 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.3532. Min Act: -0.0000

Data Index: 1186515 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.4891. Min Act: -0.0000

Data Index: 733069 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.3327. Min Act: -0.0000

Data Index: 335424 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.3663. Min Act: -0.0000

Data Index: 273105 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 5.4455. Min Range: -5.4455

Max Act: 4.1129. Min Act: -0.0000

Data Index: 234340 (C4 (Web Text))

Max Activating Token Index: 742