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

Dataset: The Pile

Neuron 2625 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1758722 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1108308 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1385905 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1357078 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1072. Min Act: -0.0000

Data Index: 288539 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1357. Min Act: -0.0000

Data Index: 596067 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1567552 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1600804 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1408. Min Act: -0.0000

Data Index: 111340 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1458. Min Act: -0.0000

Data Index: 10856 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1017692 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1347. Min Act: -0.0000

Data Index: 181624 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1806276 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.0845. Min Act: -0.0000

Data Index: 701624 (The Pile)

Max Activating Token Index: 709

Text #14

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1580878 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1768644 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1934586 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1738255 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1323. Min Act: -0.0000

Data Index: 734891 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1655987 (The Pile)

Max Activating Token Index: 995