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

Dataset: The Pile

Neuron 4986 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.7501. Min Act: -0.0000

Data Index: 415967 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5479. Min Act: -0.0000

Data Index: 962564 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5813. Min Act: -0.0000

Data Index: 742748 (The Pile)

Max Activating Token Index: 644

Text #3

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4544. Min Act: -0.0000

Data Index: 732626 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1191116 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1315618 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4868. Min Act: -0.0000

Data Index: 497690 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4286. Min Act: -0.0000

Data Index: 525144 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4272. Min Act: -0.0000

Data Index: 360178 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1429037 (The Pile)

Max Activating Token Index: 455

Text #10

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4080. Min Act: -0.0000

Data Index: 71246 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4188. Min Act: -0.0000

Data Index: 943061 (The Pile)

Max Activating Token Index: 872

Text #12

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3683. Min Act: -0.0000

Data Index: 735582 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3790. Min Act: -0.0000

Data Index: 198663 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1723426 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1460167 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3291. Min Act: -0.0000

Data Index: 307000 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1316742 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3574. Min Act: -0.0000

Data Index: 322829 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1174654 (The Pile)

Max Activating Token Index: 797