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

Dataset: The Pile

Neuron 873 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: 1.8266. Min Range: -1.8266

Max Act: 1.8266. Min Act: -0.0000

Data Index: 919944 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.5912. Min Act: -0.0000

Data Index: 1151514 (The Pile)

Max Activating Token Index: 862

Text #2

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.3350. Min Act: -0.0000

Data Index: 933511 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1178003 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.2688. Min Act: -0.0000

Data Index: 308990 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.2695. Min Act: -0.0000

Data Index: 1857015 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1703275 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1603083 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.1707. Min Act: -0.0000

Data Index: 341246 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1536359 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1424511 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1184217 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.8963. Min Act: -0.0000

Data Index: 396263 (The Pile)

Max Activating Token Index: 637

Text #13

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9873. Min Act: -0.0000

Data Index: 609429 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.0585. Min Act: -0.0000

Data Index: 26459 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9001. Min Act: -0.0000

Data Index: 3026 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1213438 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.0125. Min Act: -0.0000

Data Index: 333883 (The Pile)

Max Activating Token Index: 796

Text #18

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.0556. Min Act: -0.0000

Data Index: 215417 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1980758 (The Pile)

Max Activating Token Index: 789