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

Dataset: The Pile

Neuron 2526 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: 1.0703. Min Range: -1.0703

Max Act: 1.0703. Min Act: -0.0000

Data Index: 368319 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1039507 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1565840 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1941064 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1687541 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7244. Min Act: -0.0000

Data Index: 711599 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1299995 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7646. Min Act: -0.0000

Data Index: 563981 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.5364. Min Act: -0.0000

Data Index: 325922 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1945112 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1103911 (The Pile)

Max Activating Token Index: 980

Text #11

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.5858. Min Act: -0.0000

Data Index: 99761 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6235. Min Act: -0.0000

Data Index: 503343 (The Pile)

Max Activating Token Index: 623

Text #13

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1532735 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6422. Min Act: -0.0000

Data Index: 758621 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1026819 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1996653 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1567723 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1732741 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1203181 (The Pile)

Max Activating Token Index: 585