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

Dataset: The Pile

Neuron 4090 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3797. Min Act: -0.0000

Data Index: 519613 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1013496 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2550. Min Act: -0.0000

Data Index: 570389 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2550. Min Act: -0.0000

Data Index: 996649 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1618893 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1711. Min Act: -0.0000

Data Index: 253120 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1186704 (The Pile)

Max Activating Token Index: 892

Text #7

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2037. Min Act: -0.0000

Data Index: 856971 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1723602 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2110. Min Act: -0.0000

Data Index: 601171 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1898. Min Act: -0.0000

Data Index: 284900 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1437057 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1201874 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1479285 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1404. Min Act: -0.0000

Data Index: 725957 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1463. Min Act: -0.0000

Data Index: 97660 (The Pile)

Max Activating Token Index: 434

Text #16

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1576. Min Act: -0.0000

Data Index: 896610 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1568. Min Act: -0.0000

Data Index: 253776 (The Pile)

Max Activating Token Index: 149

Text #18

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1341192 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.1379. Min Act: -0.0000

Data Index: 993733 (The Pile)

Max Activating Token Index: 608