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

Dataset: The Pile

Neuron 2422 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.8010. Min Act: -0.0000

Data Index: 43040 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.6723. Min Act: -0.0000

Data Index: 783107 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7335. Min Act: -0.0000

Data Index: 420505 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.6683. Min Act: -0.0000

Data Index: 714576 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1029455 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.6620. Min Act: -0.0000

Data Index: 209820 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7035. Min Act: -0.0000

Data Index: 663487 (The Pile)

Max Activating Token Index: 577

Text #7

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.5628. Min Act: -0.0000

Data Index: 147960 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.4819. Min Act: -0.0000

Data Index: 1706238 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1831553 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.4999. Min Act: -0.0000

Data Index: 1022302 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.5298. Min Act: -0.0000

Data Index: 1734879 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.6349. Min Act: -0.0000

Data Index: 288815 (The Pile)

Max Activating Token Index: 718

Text #13

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.5296. Min Act: -0.0000

Data Index: 1909678 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.5082. Min Act: -0.0000

Data Index: 136792 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.5339. Min Act: -0.0000

Data Index: 151312 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.4547. Min Act: -0.0000

Data Index: 306065 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.5658. Min Act: -0.0000

Data Index: 1777170 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1892084 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.4840. Min Act: -0.0000

Data Index: 1000273 (The Pile)

Max Activating Token Index: 366