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

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

Neuron 3559 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2837. Min Range: -3.2837

Max Act: 3.2732. Min Act: -0.0000

Data Index: 1378085 (Python Code)

Max Activating Token Index: 267

Text #1

Max Range: 3.2837. Min Range: -3.2837

Max Act: 3.1069. Min Act: -0.0000

Data Index: 1590484 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 3.2837. Min Range: -3.2837

Max Act: 3.2286. Min Act: -0.0000

Data Index: 1458945 (Python Code)

Max Activating Token Index: 462

Text #3

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.9633. Min Act: -0.0000

Data Index: 1499297 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.9427. Min Act: -0.0000

Data Index: 1470890 (Python Code)

Max Activating Token Index: 775

Text #5

Max Range: 3.2837. Min Range: -3.2837

Max Act: 3.2837. Min Act: -0.0000

Data Index: 1633905 (Python Code)

Max Activating Token Index: 672

Text #6

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.8195. Min Act: -0.0000

Data Index: 1621645 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.8094. Min Act: -0.0000

Data Index: 1372872 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.5762. Min Act: -0.0000

Data Index: 1182568 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.5558. Min Act: -0.0000

Data Index: 1369026 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.7673. Min Act: -0.0000

Data Index: 1638568 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.7743. Min Act: -0.0000

Data Index: 1360012 (Python Code)

Max Activating Token Index: 605

Text #12

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.7412. Min Act: -0.0000

Data Index: 1101517 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.6735. Min Act: -0.0001

Data Index: 386955 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.6745. Min Act: -0.0000

Data Index: 1450637 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.5089. Min Act: -0.0000

Data Index: 1601352 (Python Code)

Max Activating Token Index: 944

Text #16

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.5585. Min Act: -0.0000

Data Index: 1486960 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.6923. Min Act: -0.0000

Data Index: 1384150 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.2530. Min Act: -0.0000

Data Index: 1587134 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.4885. Min Act: -0.0000

Data Index: 1342265 (C4 (Web Text))

Max Activating Token Index: 189