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

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

Neuron 16 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1081. Min Range: -1.1081

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1625143 (Python Code)

Max Activating Token Index: 665

Text #1

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1479396 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1508880 (Python Code)

Max Activating Token Index: 822

Text #3

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1617289 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 1.1081. Min Range: -1.1081

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1518355 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1592838 (Python Code)

Max Activating Token Index: 900

Text #6

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1622093 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1586615 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.7776. Min Act: -0.0000

Data Index: 444651 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1397026 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1601146 (Python Code)

Max Activating Token Index: 749

Text #11

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.7415. Min Act: -0.0000

Data Index: 497824 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1398136 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.7466. Min Act: -0.0000

Data Index: 115875 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1436932 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.7877. Min Act: -0.0001

Data Index: 1566645 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.6747. Min Act: -0.0000

Data Index: 302905 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1464129 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.7819. Min Act: -0.0000

Data Index: 640968 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.1081. Min Range: -1.1081

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1418094 (Python Code)

Max Activating Token Index: 480