Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3112 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2748. Min Act: -0.0000

Data Index: 604338 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2315. Min Act: -0.0001

Data Index: 729954 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2204. Min Act: -0.0000

Data Index: 929370 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2234. Min Act: -0.0000

Data Index: 13037 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2171. Min Act: -0.0000

Data Index: 82592 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2047. Min Act: -0.0000

Data Index: 226494 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2181. Min Act: -0.0000

Data Index: 316410 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2166. Min Act: -0.0001

Data Index: 15019 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2085. Min Act: -0.0000

Data Index: 416137 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2090. Min Act: -0.0001

Data Index: 588200 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2083. Min Act: -0.0000

Data Index: 294064 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2014. Min Act: -0.0000

Data Index: 24213 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2128. Min Act: -0.0000

Data Index: 352467 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1962. Min Act: -0.0001

Data Index: 184131 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1125651 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2024. Min Act: -0.0000

Data Index: 448117 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1992. Min Act: -0.0001

Data Index: 279055 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1888. Min Act: -0.0001

Data Index: 308689 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1061398 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1352824 (C4 (Web Text))

Max Activating Token Index: 463