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

Dataset: The Pile

Neuron 385 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: 1.2595. Min Range: -1.2595

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1296215 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.2574. Min Act: -0.0000

Data Index: 174010 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1683068 (The Pile)

Max Activating Token Index: 974

Text #3

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1316057 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.1238. Min Act: -0.0000

Data Index: 1304787 (The Pile)

Max Activating Token Index: 807

Text #5

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.1005. Min Act: -0.0000

Data Index: 735566 (The Pile)

Max Activating Token Index: 735

Text #6

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0805. Min Act: -0.0000

Data Index: 783745 (The Pile)

Max Activating Token Index: 869

Text #7

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1827720 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1416700 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9942. Min Act: -0.0000

Data Index: 748956 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1030004 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9526. Min Act: -0.0000

Data Index: 872707 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0587. Min Act: -0.0000

Data Index: 125593 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0073. Min Act: -0.0000

Data Index: 186307 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1955410 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1447652 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9620. Min Act: -0.0000

Data Index: 62510 (The Pile)

Max Activating Token Index: 379

Text #17

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1804679 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1444138 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9133. Min Act: -0.0000

Data Index: 419940 (The Pile)

Max Activating Token Index: 745