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

Dataset: The Pile

Neuron 2320 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: 0.8614. Min Range: -0.8614

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1470692 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1830405 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1088928 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1172444 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1801574 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7457. Min Act: -0.0000

Data Index: 702675 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1093484 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8118. Min Act: -0.0000

Data Index: 392443 (The Pile)

Max Activating Token Index: 79

Text #8

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1318243 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7696. Min Act: -0.0000

Data Index: 372619 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6751. Min Act: -0.0000

Data Index: 775989 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7523. Min Act: -0.0000

Data Index: 312616 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1113438 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1075929 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1732194 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1806300 (The Pile)

Max Activating Token Index: 75

Text #16

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7844. Min Act: -0.0000

Data Index: 561828 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1616346 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1718374 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7871. Min Act: -0.0000

Data Index: 132329 (The Pile)

Max Activating Token Index: 72