Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 466 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1874710 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9051. Min Act: -0.0000

Data Index: 103936 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8935. Min Act: -0.0000

Data Index: 665449 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8997. Min Act: -0.0000

Data Index: 132535 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8199. Min Act: -0.0000

Data Index: 283381 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8632. Min Act: -0.0000

Data Index: 531113 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7938. Min Act: -0.0000

Data Index: 788993 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1600465 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8087. Min Act: -0.0000

Data Index: 42636 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8558. Min Act: -0.0000

Data Index: 562008 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7756. Min Act: -0.0000

Data Index: 309759 (The Pile)

Max Activating Token Index: 63

Text #11

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8621. Min Act: -0.0000

Data Index: 521583 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8095. Min Act: -0.0000

Data Index: 567552 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1398003 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8174. Min Act: 0.0002

Data Index: 1848454 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8290. Min Act: -0.0000

Data Index: 694405 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1646914 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8098. Min Act: -0.0000

Data Index: 942042 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1632641 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7719. Min Act: -0.0000

Data Index: 444422 (The Pile)

Max Activating Token Index: 474