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

Dataset: The Pile

Neuron 3729 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.7849. Min Act: -0.0000

Data Index: 933999 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.8736. Min Act: -0.0000

Data Index: 1777931 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.6869. Min Act: -0.0000

Data Index: 938953 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.5164. Min Act: -0.0000

Data Index: 43674 (The Pile)

Max Activating Token Index: 809

Text #4

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1804702 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.2030. Min Act: -0.0000

Data Index: 747322 (The Pile)

Max Activating Token Index: 960

Text #6

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1144. Min Act: -0.0000

Data Index: 876607 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1961448 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1309368 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1107. Min Act: -0.0000

Data Index: 962286 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.8736. Min Range: -1.8736

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1732779 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.0143. Min Act: -0.0000

Data Index: 623941 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 1.8736. Min Range: -1.8736

Max Act: 0.9481. Min Act: -0.0000

Data Index: 949099 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.0481. Min Act: -0.0000

Data Index: 671160 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 1.8736. Min Range: -1.8736

Max Act: 0.9348. Min Act: -0.0000

Data Index: 986352 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 1.8736. Min Range: -1.8736

Max Act: 0.8638. Min Act: -0.0000

Data Index: 685458 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 1.8736. Min Range: -1.8736

Max Act: 0.8233. Min Act: -0.0000

Data Index: 41340 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 1.8736. Min Range: -1.8736

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1809746 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 1.8736. Min Range: -1.8736

Max Act: 0.8779. Min Act: -0.0000

Data Index: 484431 (The Pile)

Max Activating Token Index: 263

Text #19

Max Range: 1.8736. Min Range: -1.8736

Max Act: 0.6248. Min Act: -0.0000

Data Index: 994766 (The Pile)

Max Activating Token Index: 886