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

Dataset: The Pile

Neuron 5080 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: 1.8667. Min Range: -1.8667

Max Act: 1.8667. Min Act: -0.0000

Data Index: 1562484 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.5788. Min Act: -0.0000

Data Index: 914430 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.6091. Min Act: -0.0000

Data Index: 882348 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.3959. Min Act: -0.0000

Data Index: 1810803 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.4966. Min Act: -0.0000

Data Index: 1544965 (The Pile)

Max Activating Token Index: 503

Text #5

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.1877. Min Act: -0.0000

Data Index: 841189 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1710634 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.3635. Min Act: -0.0000

Data Index: 604929 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.3193. Min Act: -0.0000

Data Index: 989964 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.3826. Min Act: -0.0000

Data Index: 1794141 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1324120 (The Pile)

Max Activating Token Index: 75

Text #11

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.1613. Min Act: -0.0000

Data Index: 1497440 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1461120 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1957549 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.4443. Min Act: -0.0000

Data Index: 897097 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.2779. Min Act: -0.0000

Data Index: 1314207 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1507165 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.0406. Min Act: 0.0000

Data Index: 628425 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.2301. Min Act: -0.0000

Data Index: 412848 (The Pile)

Max Activating Token Index: 31

Text #19

Max Range: 1.8667. Min Range: -1.8667

Max Act: 1.3343. Min Act: -0.0000

Data Index: 996686 (The Pile)

Max Activating Token Index: 992