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

Dataset: The Pile

Neuron 2484 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1338. Min Act: -0.0000

Data Index: 642114 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.3497. Min Act: -0.0000

Data Index: 224978 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.2597. Min Act: -0.0000

Data Index: 1534642 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.2915. Min Act: -0.0000

Data Index: 304471 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1159663 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1939545 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1544548 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1012. Min Act: -0.0000

Data Index: 278857 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1423. Min Act: -0.0000

Data Index: 650853 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1095607 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1944805 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1403841 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1405. Min Act: -0.0000

Data Index: 393229 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1281. Min Act: -0.0000

Data Index: 1043401 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0871. Min Act: -0.0000

Data Index: 538567 (The Pile)

Max Activating Token Index: 427

Text #15

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0521. Min Act: -0.0000

Data Index: 313639 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1002. Min Act: -0.0000

Data Index: 871797 (The Pile)

Max Activating Token Index: 21

Text #17

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0964. Min Act: -0.0000

Data Index: 137815 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1659542 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1657141 (The Pile)

Max Activating Token Index: 437