Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 825 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.2078. Min Act: -0.0001

Data Index: 542434 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1961. Min Act: -0.0001

Data Index: 271596 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1954. Min Act: -0.0001

Data Index: 759202 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1826. Min Act: -0.0001

Data Index: 104362 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1798. Min Act: -0.0001

Data Index: 870521 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1045552 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1185860 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1720. Min Act: -0.0001

Data Index: 795862 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1696. Min Act: -0.0001

Data Index: 579536 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1034611 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1018266 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1030226 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1531. Min Act: -0.0001

Data Index: 601528 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1694. Min Act: -0.0001

Data Index: 454255 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1697. Min Act: -0.0001

Data Index: 810540 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1630. Min Act: -0.0001

Data Index: 539522 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1603. Min Act: -0.0001

Data Index: 291299 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1547. Min Act: -0.0001

Data Index: 552970 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1640. Min Act: -0.0001

Data Index: 667069 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.2078. Min Range: -0.2078

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1105279 (C4 (Web Text))

Max Activating Token Index: 997