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

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

Neuron 1431 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2603. Min Act: -0.0000

Data Index: 828569 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2210. Min Act: -0.0000

Data Index: 789849 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2256. Min Act: -0.0000

Data Index: 658361 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1114167 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1215235 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2053. Min Act: -0.0000

Data Index: 677058 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2112. Min Act: -0.0000

Data Index: 683770 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2025. Min Act: -0.0001

Data Index: 507491 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1963. Min Act: -0.0001

Data Index: 251527 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1188149 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1988. Min Act: -0.0000

Data Index: 705174 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2006. Min Act: -0.0000

Data Index: 940785 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2068. Min Act: -0.0001

Data Index: 85840 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1953. Min Act: -0.0001

Data Index: 534408 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1246535 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1299869 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1870. Min Act: -0.0001

Data Index: 1182335 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1931. Min Act: -0.0001

Data Index: 731952 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1746. Min Act: -0.0001

Data Index: 331840 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1249822 (C4 (Web Text))

Max Activating Token Index: 289