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

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

Neuron 104 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3823. Min Range: -2.3823

Max Act: 2.3823. Min Act: -0.0000

Data Index: 1214740 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 2.3823. Min Range: -2.3823

Max Act: 2.2617. Min Act: -0.0000

Data Index: 1443436 (Python Code)

Max Activating Token Index: 325

Text #2

Max Range: 2.3823. Min Range: -2.3823

Max Act: 2.1964. Min Act: -0.0000

Data Index: 1507253 (Python Code)

Max Activating Token Index: 266

Text #3

Max Range: 2.3823. Min Range: -2.3823

Max Act: 2.1030. Min Act: -0.0000

Data Index: 1499299 (Python Code)

Max Activating Token Index: 676

Text #4

Max Range: 2.3823. Min Range: -2.3823

Max Act: 2.0254. Min Act: -0.0000

Data Index: 1586051 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.9021. Min Act: -0.0000

Data Index: 478176 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.9739. Min Act: -0.0000

Data Index: 10939 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.9064. Min Act: -0.0000

Data Index: 156461 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.9008. Min Act: -0.0000

Data Index: 1620525 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.8641. Min Act: -0.0000

Data Index: 1368001 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.6756. Min Act: -0.0000

Data Index: 1654580 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.6770. Min Act: -0.0000

Data Index: 1492846 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.6569. Min Act: -0.0000

Data Index: 1609086 (Python Code)

Max Activating Token Index: 906

Text #13

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.7607. Min Act: -0.0000

Data Index: 1595849 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.7688. Min Act: -0.0000

Data Index: 1554576 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.7325. Min Act: -0.0000

Data Index: 1623065 (Python Code)

Max Activating Token Index: 552

Text #16

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.6215. Min Act: -0.0000

Data Index: 1374397 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.6126. Min Act: -0.0000

Data Index: 1521431 (Python Code)

Max Activating Token Index: 981

Text #18

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.6883. Min Act: -0.0000

Data Index: 1442219 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 2.3823. Min Range: -2.3823

Max Act: 1.6900. Min Act: -0.0000

Data Index: 592934 (C4 (Web Text))

Max Activating Token Index: 30