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

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

Neuron 4745 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: 4.2005. Min Range: -4.2005

Max Act: 4.1058. Min Act: -0.0000

Data Index: 1483007 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 4.2005. Min Range: -4.2005

Max Act: 4.2005. Min Act: -0.0000

Data Index: 1533963 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.9330. Min Act: -0.0000

Data Index: 1569670 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.4034. Min Act: -0.0000

Data Index: 1636999 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.6788. Min Act: -0.0000

Data Index: 1554317 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.7319. Min Act: -0.0000

Data Index: 1411903 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.4725. Min Act: -0.0000

Data Index: 1656367 (Python Code)

Max Activating Token Index: 185

Text #7

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.2617. Min Act: -0.0000

Data Index: 1472389 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.2202. Min Act: -0.0000

Data Index: 1563847 (Python Code)

Max Activating Token Index: 969

Text #9

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.2020. Min Act: -0.0000

Data Index: 1484602 (Python Code)

Max Activating Token Index: 164

Text #10

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.2240. Min Act: -0.0000

Data Index: 1431710 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.1629. Min Act: -0.0000

Data Index: 1409238 (Python Code)

Max Activating Token Index: 838

Text #12

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.2828. Min Act: -0.0000

Data Index: 354566 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 4.2005. Min Range: -4.2005

Max Act: 2.9923. Min Act: -0.0000

Data Index: 445706 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.0747. Min Act: -0.0000

Data Index: 1594880 (Python Code)

Max Activating Token Index: 159

Text #15

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.0842. Min Act: -0.0000

Data Index: 1393663 (Python Code)

Max Activating Token Index: 50

Text #16

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.0589. Min Act: -0.0000

Data Index: 1476736 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 4.2005. Min Range: -4.2005

Max Act: 2.9011. Min Act: -0.0000

Data Index: 1597138 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 4.2005. Min Range: -4.2005

Max Act: 2.8746. Min Act: -0.0000

Data Index: 1413325 (Python Code)

Max Activating Token Index: 88

Text #19

Max Range: 4.2005. Min Range: -4.2005

Max Act: 3.1141. Min Act: -0.0000

Data Index: 1374747 (Python Code)

Max Activating Token Index: 926