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

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

Neuron 3759 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.7562. Min Act: -0.0000

Data Index: 390478 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.6628. Min Act: -0.0000

Data Index: 1649994 (Python Code)

Max Activating Token Index: 681

Text #2

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.2714. Min Act: -0.0000

Data Index: 1108145 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1395878 (Python Code)

Max Activating Token Index: 931

Text #4

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1602259 (Python Code)

Max Activating Token Index: 670

Text #5

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1376189 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.1906. Min Act: -0.0000

Data Index: 901017 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.1964. Min Act: -0.0000

Data Index: 1637754 (Python Code)

Max Activating Token Index: 873

Text #8

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.1136. Min Act: -0.0000

Data Index: 736499 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1417973 (Python Code)

Max Activating Token Index: 365

Text #10

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.0695. Min Act: -0.0000

Data Index: 921222 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.1940. Min Act: -0.0000

Data Index: 1513986 (Python Code)

Max Activating Token Index: 702

Text #12

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.1060. Min Act: -0.0000

Data Index: 1484863 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1501342 (Python Code)

Max Activating Token Index: 266

Text #14

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1411330 (Python Code)

Max Activating Token Index: 1008

Text #15

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1471170 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.0005. Min Act: -0.0000

Data Index: 1623888 (Python Code)

Max Activating Token Index: 420

Text #17

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1585955 (Python Code)

Max Activating Token Index: 811

Text #18

Max Range: 1.7562. Min Range: -1.7562

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1005742 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 1.7562. Min Range: -1.7562

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1380308 (Python Code)

Max Activating Token Index: 81