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

Dataset: The Pile

Neuron 2125 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1926307 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.0858. Min Act: -0.0000

Data Index: 593168 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.0176. Min Act: -0.0000

Data Index: 962783 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.0928. Min Act: -0.0000

Data Index: 91910 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.0540. Min Act: -0.0000

Data Index: 591504 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9169. Min Act: -0.0000

Data Index: 408583 (The Pile)

Max Activating Token Index: 595

Text #6

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1650568 (The Pile)

Max Activating Token Index: 652

Text #7

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9814. Min Act: -0.0000

Data Index: 419367 (The Pile)

Max Activating Token Index: 833

Text #8

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.0268. Min Act: -0.0000

Data Index: 352070 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1013196 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.0904. Min Act: -0.0000

Data Index: 593624 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1913224 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9893. Min Act: -0.0000

Data Index: 475935 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1092648 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9773. Min Act: -0.0000

Data Index: 135427 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1912503 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1186229 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1194160 (The Pile)

Max Activating Token Index: 963

Text #18

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1636371 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8818. Min Act: -0.0000

Data Index: 666383 (The Pile)

Max Activating Token Index: 705