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

Dataset: The Pile

Neuron 3603 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: 1.1539. Min Range: -1.1539

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1483889 (The Pile)

Max Activating Token Index: 514

Text #1

Max Range: 1.1539. Min Range: -1.1539

Max Act: 1.0646. Min Act: -0.0000

Data Index: 188226 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 1.1539. Min Range: -1.1539

Max Act: 1.1409. Min Act: -0.0000

Data Index: 836308 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 1.1539. Min Range: -1.1539

Max Act: 1.0897. Min Act: -0.0000

Data Index: 680532 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.9748. Min Act: -0.0000

Data Index: 273291 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 1.1539. Min Range: -1.1539

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1843444 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1247937 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.9558. Min Act: -0.0000

Data Index: 132833 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1338605 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1800103 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1957543 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.9324. Min Act: -0.0000

Data Index: 665240 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.8155. Min Act: -0.0000

Data Index: 627383 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1520625 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1444456 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7758. Min Act: -0.0000

Data Index: 978449 (The Pile)

Max Activating Token Index: 692

Text #16

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1672 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7983. Min Act: -0.0000

Data Index: 256386 (The Pile)

Max Activating Token Index: 804

Text #18

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.8126. Min Act: -0.0000

Data Index: 137604 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1418116 (The Pile)

Max Activating Token Index: 563