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

Dataset: The Pile

Neuron 4050 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: 0.6337. Min Range: -0.6337

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1492378 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1342486 (The Pile)

Max Activating Token Index: 166

Text #2

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5486. Min Act: -0.0000

Data Index: 894709 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5782. Min Act: -0.0000

Data Index: 880283 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5748. Min Act: -0.0000

Data Index: 387824 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1315461 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5744. Min Act: -0.0000

Data Index: 182651 (The Pile)

Max Activating Token Index: 398

Text #7

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1740886 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1827726 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5282. Min Act: -0.0000

Data Index: 64146 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1129863 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5223. Min Act: -0.0000

Data Index: 604787 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1988646 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1271270 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5206. Min Act: -0.0000

Data Index: 922349 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1655163 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1657620 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1476775 (The Pile)

Max Activating Token Index: 302

Text #18

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1079569 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1603593 (The Pile)

Max Activating Token Index: 55