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

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

Neuron 4443 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: 2.6790. Min Range: -2.6790

Max Act: 2.6790. Min Act: -0.0001

Data Index: 697759 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 2.6790. Min Range: -2.6790

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1002087 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 2.6790. Min Range: -2.6790

Max Act: 2.2178. Min Act: -0.0000

Data Index: 784857 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.9265. Min Act: -0.0000

Data Index: 646320 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.7631. Min Act: -0.0000

Data Index: 1170095 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.6402. Min Act: -0.0000

Data Index: 78497 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.8062. Min Act: -0.0000

Data Index: 372399 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.7427. Min Act: -0.0000

Data Index: 674855 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.6550. Min Act: -0.0000

Data Index: 196931 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.7534. Min Act: -0.0000

Data Index: 1108971 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.5367. Min Act: -0.0000

Data Index: 650361 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.5119. Min Act: -0.0000

Data Index: 866500 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.6396. Min Act: -0.0000

Data Index: 319749 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.6879. Min Act: -0.0000

Data Index: 333985 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.6301. Min Act: -0.0000

Data Index: 78182 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.6613. Min Act: -0.0000

Data Index: 629340 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.5209. Min Act: -0.0000

Data Index: 961174 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.6910. Min Act: -0.0000

Data Index: 1088850 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.6732. Min Act: -0.0000

Data Index: 1159693 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 2.6790. Min Range: -2.6790

Max Act: 1.4475. Min Act: -0.0000

Data Index: 588114 (C4 (Web Text))

Max Activating Token Index: 526