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

Dataset: The Pile

Neuron 3772 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: 1.0166. Min Range: -1.0166

Max Act: 1.0023. Min Act: -0.0000

Data Index: 313066 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 1.0166. Min Range: -1.0166

Max Act: 1.0166. Min Act: -0.0000

Data Index: 981096 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.9607. Min Act: -0.0000

Data Index: 799285 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.9887. Min Act: -0.0000

Data Index: 732127 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.9774. Min Act: -0.0000

Data Index: 932497 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1930001 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1830666 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8583. Min Act: -0.0000

Data Index: 436408 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8518. Min Act: -0.0000

Data Index: 212442 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1262355 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.9006. Min Act: -0.0000

Data Index: 93265 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8667. Min Act: -0.0000

Data Index: 351682 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1451153 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1598847 (The Pile)

Max Activating Token Index: 832

Text #14

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8995. Min Act: -0.0000

Data Index: 923035 (The Pile)

Max Activating Token Index: 684

Text #15

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8384. Min Act: -0.0000

Data Index: 205322 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1227216 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8035. Min Act: -0.0000

Data Index: 840945 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1488192 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1853526 (The Pile)

Max Activating Token Index: 967