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

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

Neuron 602 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.7620. Min Act: -0.0000

Data Index: 1444962 (Python Code)

Max Activating Token Index: 481

Text #1

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.5396. Min Act: -0.0000

Data Index: 1465385 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.5778. Min Act: -0.0000

Data Index: 1601025 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.5516. Min Act: -0.0000

Data Index: 1406217 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.5266. Min Act: -0.0000

Data Index: 1450689 (Python Code)

Max Activating Token Index: 408

Text #5

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.5099. Min Act: -0.0000

Data Index: 1596171 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.4531. Min Act: -0.0000

Data Index: 1534025 (Python Code)

Max Activating Token Index: 1017

Text #7

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.3887. Min Act: -0.0000

Data Index: 1514449 (Python Code)

Max Activating Token Index: 840

Text #8

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.5090. Min Act: -0.0000

Data Index: 1573138 (Python Code)

Max Activating Token Index: 266

Text #9

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.2343. Min Act: -0.0000

Data Index: 1635919 (Python Code)

Max Activating Token Index: 286

Text #10

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.3497. Min Act: -0.0000

Data Index: 1560253 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.4107. Min Act: -0.0000

Data Index: 1449741 (Python Code)

Max Activating Token Index: 644

Text #12

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.0084. Min Act: -0.0000

Data Index: 574078 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.1060. Min Act: -0.0000

Data Index: 1575631 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.2131. Min Act: -0.0000

Data Index: 1391920 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.0286. Min Act: -0.0000

Data Index: 1433333 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.1879. Min Act: -0.0000

Data Index: 1603975 (Python Code)

Max Activating Token Index: 121

Text #17

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.0040. Min Act: -0.0000

Data Index: 1652280 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.2214. Min Act: -0.0000

Data Index: 1389812 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 2.7620. Min Range: -2.7620

Max Act: 2.0861. Min Act: -0.0000

Data Index: 606916 (C4 (Web Text))

Max Activating Token Index: 960