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

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

Neuron 5689 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: 2.0829. Min Range: -2.0829

Max Act: 2.0829. Min Act: 0.0000

Data Index: 1607824 (Python Code)

Max Activating Token Index: 734

Text #1

Max Range: 2.0829. Min Range: -2.0829

Max Act: 2.0007. Min Act: -0.0000

Data Index: 1430011 (Python Code)

Max Activating Token Index: 1004

Text #2

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.8285. Min Act: 0.0000

Data Index: 1435961 (Python Code)

Max Activating Token Index: 902

Text #3

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.8055. Min Act: -0.0000

Data Index: 1623971 (Python Code)

Max Activating Token Index: 381

Text #4

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.7039. Min Act: -0.0000

Data Index: 1432623 (Python Code)

Max Activating Token Index: 1005

Text #5

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.6484. Min Act: -0.0000

Data Index: 371442 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.4505. Min Act: -0.0000

Data Index: 1619471 (Python Code)

Max Activating Token Index: 316

Text #7

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.5009. Min Act: -0.0000

Data Index: 85351 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.5879. Min Act: -0.0000

Data Index: 1546584 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.6564. Min Act: -0.0000

Data Index: 1008738 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.5735. Min Act: -0.0000

Data Index: 1425323 (Python Code)

Max Activating Token Index: 175

Text #11

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.5599. Min Act: 0.0000

Data Index: 1509195 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.4540. Min Act: -0.0000

Data Index: 1559575 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.5447. Min Act: -0.0000

Data Index: 1439830 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.4357. Min Act: -0.0000

Data Index: 1603877 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.5076. Min Act: 0.0000

Data Index: 1385825 (Python Code)

Max Activating Token Index: 610

Text #16

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.4261. Min Act: -0.0000

Data Index: 1189932 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.5108. Min Act: -0.0000

Data Index: 1290337 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1491323 (Python Code)

Max Activating Token Index: 399

Text #19

Max Range: 2.0829. Min Range: -2.0829

Max Act: 1.4938. Min Act: 0.0000

Data Index: 1556682 (Python Code)

Max Activating Token Index: 81