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

Dataset: The Pile

Neuron 2784 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: 0.5983. Min Range: -0.5983

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1561345 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1180215 (The Pile)

Max Activating Token Index: 864

Text #2

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1250590 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1249231 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5263. Min Act: -0.0000

Data Index: 844478 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5622. Min Act: -0.0000

Data Index: 446936 (The Pile)

Max Activating Token Index: 952

Text #6

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5432. Min Act: -0.0000

Data Index: 786191 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1575080 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1973991 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1718125 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1943342 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5093. Min Act: -0.0000

Data Index: 441252 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5221. Min Act: -0.0000

Data Index: 134417 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1632646 (The Pile)

Max Activating Token Index: 882

Text #14

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5039. Min Act: -0.0000

Data Index: 725774 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4933. Min Act: -0.0000

Data Index: 703861 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4799. Min Act: -0.0000

Data Index: 28096 (The Pile)

Max Activating Token Index: 318

Text #17

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1773518 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4716. Min Act: -0.0000

Data Index: 956076 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4699. Min Act: -0.0000

Data Index: 288078 (The Pile)

Max Activating Token Index: 21