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

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

Neuron 4940 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: 1.5634. Min Range: -1.5634

Max Act: 1.5634. Min Act: -0.0000

Data Index: 975121 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.5022. Min Act: -0.0000

Data Index: 225987 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.3465. Min Act: -0.0000

Data Index: 254020 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.2619. Min Act: -0.0000

Data Index: 851953 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1097364 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.2878. Min Act: -0.0000

Data Index: 1415955 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.2105. Min Act: -0.0000

Data Index: 1612356 (Python Code)

Max Activating Token Index: 602

Text #7

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1447139 (Python Code)

Max Activating Token Index: 42

Text #8

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1566771 (Python Code)

Max Activating Token Index: 214

Text #9

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1646679 (Python Code)

Max Activating Token Index: 450

Text #10

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1539543 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1401728 (Python Code)

Max Activating Token Index: 109

Text #12

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1463956 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1333. Min Act: -0.0000

Data Index: 1470081 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1070. Min Act: -0.0000

Data Index: 1571194 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1426339 (Python Code)

Max Activating Token Index: 459

Text #16

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1400411 (Python Code)

Max Activating Token Index: 458

Text #17

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.0836. Min Act: -0.0000

Data Index: 1578848 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1533161 (Python Code)

Max Activating Token Index: 768

Text #19

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1511646 (Python Code)

Max Activating Token Index: 273