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

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

Neuron 2108 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0000

Data Index: 43910 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1135567 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1322820 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1196995 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1038. Min Act: -0.0000

Data Index: 145024 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1109. Min Act: -0.0000

Data Index: 489036 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1580703 (Python Code)

Max Activating Token Index: 600

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1024. Min Act: -0.0000

Data Index: 591203 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1492017 (Python Code)

Max Activating Token Index: 944

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1002. Min Act: -0.0000

Data Index: 109611 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1218765 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1411548 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0952. Min Act: -0.0000

Data Index: 132593 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0984. Min Act: -0.0000

Data Index: 92588 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0910. Min Act: -0.0000

Data Index: 283422 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0975. Min Act: -0.0000

Data Index: 45426 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1447663 (Python Code)

Max Activating Token Index: 435

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1021856 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1656974 (Python Code)

Max Activating Token Index: 892

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1323303 (C4 (Web Text))

Max Activating Token Index: 646