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

Dataset: The Pile

Neuron 3245 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.8079. Min Act: -0.0000

Data Index: 537218 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1117629 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7747. Min Act: -0.0000

Data Index: 553802 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1503319 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1335302 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1085851 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7185. Min Act: -0.0000

Data Index: 930608 (The Pile)

Max Activating Token Index: 719

Text #7

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7806. Min Act: -0.0000

Data Index: 445542 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7479. Min Act: -0.0000

Data Index: 681747 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1153708 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1020778 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.6828. Min Act: -0.0000

Data Index: 773511 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.8050. Min Act: -0.0000

Data Index: 570697 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1974961 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1940408 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1975009 (The Pile)

Max Activating Token Index: 453

Text #16

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1755318 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1376106 (The Pile)

Max Activating Token Index: 336

Text #18

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1528725 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.8118. Min Range: -0.8118

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1855674 (The Pile)

Max Activating Token Index: 168