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

Dataset: The Pile

Neuron 722 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: 0.8165. Min Range: -0.8165

Max Act: 0.8004. Min Act: -0.0000

Data Index: 780237 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1664777 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1200596 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6810. Min Act: -0.0000

Data Index: 862050 (The Pile)

Max Activating Token Index: 899

Text #4

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1311254 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1010651 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1092065 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6837. Min Act: 0.0000

Data Index: 248886 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6258. Min Act: -0.0000

Data Index: 550072 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1965561 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6201. Min Act: -0.0000

Data Index: 387609 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6535. Min Act: -0.0000

Data Index: 726760 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6134. Min Act: -0.0000

Data Index: 623380 (The Pile)

Max Activating Token Index: 299

Text #13

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6180. Min Act: -0.0000

Data Index: 863604 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1635243 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1244632 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6558. Min Act: -0.0000

Data Index: 446468 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.5625. Min Act: -0.0000

Data Index: 368778 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.5922. Min Act: -0.0000

Data Index: 442935 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1141803 (The Pile)

Max Activating Token Index: 507