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

Dataset: The Pile

Neuron 2934 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: 1.9734. Min Range: -1.9734

Max Act: 1.9574. Min Act: 0.0000

Data Index: 291791 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.9734. Min Act: -0.0000

Data Index: 403080 (The Pile)

Max Activating Token Index: 618

Text #2

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.7330. Min Act: -0.0000

Data Index: 617141 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.8008. Min Act: -0.0000

Data Index: 41013 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.9169. Min Act: -0.0000

Data Index: 642222 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.7694. Min Act: -0.0000

Data Index: 143660 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.7103. Min Act: -0.0000

Data Index: 505953 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.6680. Min Act: -0.0000

Data Index: 1558332 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.6800. Min Act: -0.0000

Data Index: 1478436 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.6257. Min Act: -0.0000

Data Index: 567966 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.5165. Min Act: -0.0000

Data Index: 1912568 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.4988. Min Act: -0.0000

Data Index: 1596976 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.4815. Min Act: -0.0000

Data Index: 1941139 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.5854. Min Act: -0.0000

Data Index: 1097230 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.4913. Min Act: -0.0000

Data Index: 792651 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1628048 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.4744. Min Act: -0.0000

Data Index: 525406 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.2981. Min Act: -0.0000

Data Index: 72366 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1675695 (The Pile)

Max Activating Token Index: 590

Text #19

Max Range: 1.9734. Min Range: -1.9734

Max Act: 1.5230. Min Act: -0.0000

Data Index: 294364 (The Pile)

Max Activating Token Index: 324