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

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

Neuron 3242 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: 3.4789. Min Range: -3.4789

Max Act: 3.4789. Min Act: -0.0000

Data Index: 1378305 (Python Code)

Max Activating Token Index: 357

Text #1

Max Range: 3.4789. Min Range: -3.4789

Max Act: 3.3145. Min Act: -0.0000

Data Index: 1484646 (Python Code)

Max Activating Token Index: 413

Text #2

Max Range: 3.4789. Min Range: -3.4789

Max Act: 3.3249. Min Act: -0.0000

Data Index: 1611996 (Python Code)

Max Activating Token Index: 408

Text #3

Max Range: 3.4789. Min Range: -3.4789

Max Act: 3.1237. Min Act: -0.0000

Data Index: 1483073 (Python Code)

Max Activating Token Index: 842

Text #4

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.9492. Min Act: -0.0000

Data Index: 1555678 (Python Code)

Max Activating Token Index: 760

Text #5

Max Range: 3.4789. Min Range: -3.4789

Max Act: 3.0853. Min Act: -0.0000

Data Index: 1628106 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 3.4789. Min Range: -3.4789

Max Act: 3.0525. Min Act: -0.0000

Data Index: 519809 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.8499. Min Act: -0.0000

Data Index: 207942 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.7401. Min Act: -0.0000

Data Index: 75804 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.8967. Min Act: -0.0000

Data Index: 250023 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.6927. Min Act: -0.0000

Data Index: 798091 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.7078. Min Act: -0.0000

Data Index: 271059 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.6273. Min Act: -0.0000

Data Index: 909133 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.7565. Min Act: -0.0000

Data Index: 161290 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.7033. Min Act: -0.0000

Data Index: 943570 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.5623. Min Act: -0.0000

Data Index: 723485 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.2886. Min Act: -0.0000

Data Index: 915304 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.3657. Min Act: -0.0000

Data Index: 1314334 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.2499. Min Act: -0.0000

Data Index: 1606800 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 3.4789. Min Range: -3.4789

Max Act: 2.2024. Min Act: -0.0000

Data Index: 1589272 (Python Code)

Max Activating Token Index: 94