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

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

Neuron 2596 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2732. Min Act: -0.0001

Data Index: 528850 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2757. Min Act: -0.0001

Data Index: 425123 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2521. Min Act: -0.0001

Data Index: 571308 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1215991 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2286. Min Act: -0.0001

Data Index: 257812 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2199. Min Act: -0.0001

Data Index: 1044587 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2322. Min Act: -0.0001

Data Index: 727288 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2242. Min Act: -0.0001

Data Index: 1262453 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2109. Min Act: -0.0001

Data Index: 467160 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1943. Min Act: -0.0001

Data Index: 1167986 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2071. Min Act: -0.0001

Data Index: 898229 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2067. Min Act: -0.0001

Data Index: 158293 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1933. Min Act: -0.0001

Data Index: 1268782 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1939. Min Act: -0.0001

Data Index: 799980 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1938. Min Act: -0.0001

Data Index: 568472 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1943. Min Act: -0.0001

Data Index: 536824 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1338101 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1831. Min Act: -0.0001

Data Index: 582144 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1880. Min Act: -0.0001

Data Index: 256890 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1823. Min Act: -0.0001

Data Index: 1040189 (C4 (Web Text))

Max Activating Token Index: 51