Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1912 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1500990 (Python Code)

Max Activating Token Index: 592

Text #1

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1252. Min Act: -0.0002

Data Index: 1399796 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1640821 (Python Code)

Max Activating Token Index: 618

Text #3

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1388958 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1514929 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1474689 (Python Code)

Max Activating Token Index: 309

Text #6

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1420882 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1090. Min Act: -0.0002

Data Index: 281418 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1470730 (Python Code)

Max Activating Token Index: 1012

Text #9

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1639819 (Python Code)

Max Activating Token Index: 159

Text #10

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1408486 (Python Code)

Max Activating Token Index: 979

Text #11

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1641628 (Python Code)

Max Activating Token Index: 865

Text #12

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1055. Min Act: -0.0002

Data Index: 131684 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1579579 (Python Code)

Max Activating Token Index: 85

Text #14

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1047. Min Act: -0.0002

Data Index: 280766 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1215682 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1121. Min Act: -0.0002

Data Index: 1443819 (Python Code)

Max Activating Token Index: 725

Text #17

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1096. Min Act: -0.0002

Data Index: 852484 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1391533 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1604485 (Python Code)

Max Activating Token Index: 136