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

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

Neuron 4999 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: 2.6895. Min Range: -2.6895

Max Act: 2.6895. Min Act: -0.0000

Data Index: 1619580 (Python Code)

Max Activating Token Index: 635

Text #1

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.0259. Min Act: -0.0000

Data Index: 1526002 (Python Code)

Max Activating Token Index: 215

Text #2

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.7809. Min Act: -0.0000

Data Index: 1567228 (Python Code)

Max Activating Token Index: 327

Text #3

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.8205. Min Act: -0.0000

Data Index: 1578221 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.8042. Min Act: -0.0000

Data Index: 1636666 (Python Code)

Max Activating Token Index: 721

Text #5

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.7815. Min Act: -0.0000

Data Index: 1617858 (Python Code)

Max Activating Token Index: 416

Text #6

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.7509. Min Act: -0.0000

Data Index: 1596910 (Python Code)

Max Activating Token Index: 795

Text #7

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.6347. Min Act: -0.0000

Data Index: 1619082 (Python Code)

Max Activating Token Index: 335

Text #8

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.5939. Min Act: -0.0000

Data Index: 1430747 (Python Code)

Max Activating Token Index: 422

Text #9

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.5994. Min Act: -0.0000

Data Index: 1373881 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.4970. Min Act: -0.0000

Data Index: 1444903 (Python Code)

Max Activating Token Index: 681

Text #11

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1631378 (Python Code)

Max Activating Token Index: 539

Text #12

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1504154 (Python Code)

Max Activating Token Index: 390

Text #13

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.5928. Min Act: -0.0000

Data Index: 1616120 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1391039 (Python Code)

Max Activating Token Index: 486

Text #15

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.5678. Min Act: -0.0000

Data Index: 1366620 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1651885 (Python Code)

Max Activating Token Index: 205

Text #17

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.4932. Min Act: -0.0000

Data Index: 1519149 (Python Code)

Max Activating Token Index: 623

Text #18

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.4820. Min Act: -0.0000

Data Index: 1459347 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 2.6895. Min Range: -2.6895

Max Act: 1.4604. Min Act: -0.0000

Data Index: 1472372 (Python Code)

Max Activating Token Index: 554