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

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

Neuron 4281 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: 2.4862. Min Range: -2.4862

Max Act: 2.4862. Min Act: -0.0000

Data Index: 490698 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 2.4862. Min Range: -2.4862

Max Act: 2.3275. Min Act: -0.0000

Data Index: 343312 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 2.4862. Min Range: -2.4862

Max Act: 2.1031. Min Act: 0.0000

Data Index: 242962 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 2.4862. Min Range: -2.4862

Max Act: 2.0848. Min Act: -0.0000

Data Index: 1144104 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 2.4862. Min Range: -2.4862

Max Act: 2.0128. Min Act: -0.0000

Data Index: 1226369 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.9863. Min Act: -0.0000

Data Index: 605566 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.9656. Min Act: -0.0000

Data Index: 596771 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.9397. Min Act: 0.0001

Data Index: 1192426 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8980. Min Act: -0.0000

Data Index: 1244789 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8815. Min Act: -0.0000

Data Index: 1055593 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8684. Min Act: -0.0000

Data Index: 50155 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8573. Min Act: -0.0000

Data Index: 418808 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8467. Min Act: -0.0000

Data Index: 75065 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8289. Min Act: -0.0000

Data Index: 105533 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8308. Min Act: -0.0000

Data Index: 192972 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8184. Min Act: -0.0000

Data Index: 427549 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8701. Min Act: -0.0000

Data Index: 800319 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.7727. Min Act: 0.0000

Data Index: 266318 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.7663. Min Act: -0.0000

Data Index: 1210979 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 2.4862. Min Range: -2.4862

Max Act: 1.8685. Min Act: -0.0000

Data Index: 1298815 (C4 (Web Text))

Max Activating Token Index: 887