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

Dataset: The Pile

Neuron 1722 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.4279. Min Act: -0.0000

Data Index: 1140036 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.2294. Min Act: -0.0000

Data Index: 200654 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.3473. Min Act: -0.0000

Data Index: 866267 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.2770. Min Act: -0.0000

Data Index: 749668 (The Pile)

Max Activating Token Index: 437

Text #4

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.2440. Min Act: -0.0000

Data Index: 143665 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1893557 (The Pile)

Max Activating Token Index: 125

Text #6

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1541257 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1627. Min Act: -0.0000

Data Index: 1012528 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1226425 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1097. Min Act: 0.0000

Data Index: 1342374 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1797. Min Act: -0.0000

Data Index: 654792 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1736250 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1773430 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.2284. Min Act: -0.0000

Data Index: 1986146 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1394980 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1029319 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1350641 (The Pile)

Max Activating Token Index: 335

Text #17

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1935822 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1242. Min Act: -0.0000

Data Index: 987056 (The Pile)

Max Activating Token Index: 76

Text #19

Max Range: 1.4279. Min Range: -1.4279

Max Act: 1.1183. Min Act: -0.0000

Data Index: 256201 (The Pile)

Max Activating Token Index: 41