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

Dataset: The Pile

Neuron 3700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1448. Min Range: -1.1448

Max Act: 1.1448. Min Act: -0.0001

Data Index: 1297329 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 1.1448. Min Range: -1.1448

Max Act: 1.0282. Min Act: -0.0001

Data Index: 287450 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1444225 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9474. Min Act: -0.0000

Data Index: 156953 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1007425 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1257966 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9593. Min Act: -0.0000

Data Index: 371057 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9145. Min Act: -0.0000

Data Index: 973597 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8566. Min Act: -0.0000

Data Index: 644117 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8759. Min Act: -0.0000

Data Index: 373177 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9213. Min Act: -0.0000

Data Index: 40953 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1692997 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8740. Min Act: -0.0000

Data Index: 466160 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8880. Min Act: -0.0000

Data Index: 597784 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1504579 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8290. Min Act: -0.0000

Data Index: 386986 (The Pile)

Max Activating Token Index: 834

Text #16

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8426. Min Act: -0.0000

Data Index: 136011 (The Pile)

Max Activating Token Index: 4

Text #17

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1501715 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1556437 (The Pile)

Max Activating Token Index: 721

Text #19

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1514459 (The Pile)

Max Activating Token Index: 884