Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1032 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.9802. Min Act: -0.0000

Data Index: 1373895 (Python Code)

Max Activating Token Index: 224

Text #1

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.5491. Min Act: -0.0000

Data Index: 1478154 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.7251. Min Act: -0.0000

Data Index: 1391292 (Python Code)

Max Activating Token Index: 870

Text #3

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.3108. Min Act: -0.0001

Data Index: 1634313 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.4131. Min Act: -0.0000

Data Index: 1449576 (Python Code)

Max Activating Token Index: 447

Text #5

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.3777. Min Act: -0.0000

Data Index: 1446546 (Python Code)

Max Activating Token Index: 741

Text #6

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.3866. Min Act: -0.0000

Data Index: 1584250 (Python Code)

Max Activating Token Index: 761

Text #7

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.2600. Min Act: -0.0000

Data Index: 1595823 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.3539. Min Act: -0.0000

Data Index: 1180121 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.2357. Min Act: -0.0000

Data Index: 1437260 (Python Code)

Max Activating Token Index: 828

Text #10

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.3501. Min Act: -0.0000

Data Index: 1401699 (Python Code)

Max Activating Token Index: 962

Text #11

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.1835. Min Act: -0.0000

Data Index: 1490302 (Python Code)

Max Activating Token Index: 937

Text #12

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.1751. Min Act: -0.0000

Data Index: 1628740 (Python Code)

Max Activating Token Index: 119

Text #13

Max Range: 2.9802. Min Range: -2.9802

Max Act: 1.9761. Min Act: -0.0000

Data Index: 1508228 (Python Code)

Max Activating Token Index: 875

Text #14

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.3894. Min Act: -0.0000

Data Index: 1563085 (Python Code)

Max Activating Token Index: 364

Text #15

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.4816. Min Act: -0.0000

Data Index: 151738 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.3446. Min Act: -0.0000

Data Index: 1605119 (Python Code)

Max Activating Token Index: 970

Text #17

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.1299. Min Act: -0.0000

Data Index: 1545971 (Python Code)

Max Activating Token Index: 561

Text #18

Max Range: 2.9802. Min Range: -2.9802

Max Act: 2.0669. Min Act: -0.0000

Data Index: 1477674 (Python Code)

Max Activating Token Index: 717

Text #19

Max Range: 2.9802. Min Range: -2.9802

Max Act: 1.8934. Min Act: -0.0000

Data Index: 1444010 (Python Code)

Max Activating Token Index: 842