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

Dataset: The Pile

Neuron 3877 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.6818. Min Act: -0.0000

Data Index: 1994760 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.4372. Min Act: -0.0000

Data Index: 917225 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.5217. Min Act: -0.0000

Data Index: 1647642 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.2868. Min Act: -0.0000

Data Index: 1377218 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3565. Min Act: -0.0000

Data Index: 215727 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3762. Min Act: -0.0000

Data Index: 924992 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3649. Min Act: -0.0000

Data Index: 1481296 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3621. Min Act: -0.0000

Data Index: 1125332 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3458. Min Act: -0.0000

Data Index: 1652436 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3427. Min Act: -0.0000

Data Index: 727429 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3347. Min Act: -0.0000

Data Index: 177726 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3073. Min Act: -0.0000

Data Index: 1559270 (The Pile)

Max Activating Token Index: 557

Text #12

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.2989. Min Act: -0.0000

Data Index: 1486859 (The Pile)

Max Activating Token Index: 193

Text #13

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3642. Min Act: -0.0000

Data Index: 20792 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.1964. Min Act: -0.0000

Data Index: 693103 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.1883. Min Act: -0.0000

Data Index: 796389 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.1910. Min Act: -0.0000

Data Index: 1633044 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.1601. Min Act: -0.0000

Data Index: 82467 (The Pile)

Max Activating Token Index: 472

Text #18

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.0145. Min Act: -0.0000

Data Index: 309229 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 3.6818. Min Range: -3.6818

Max Act: 3.3194. Min Act: -0.0000

Data Index: 574163 (The Pile)

Max Activating Token Index: 296