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

Dataset: The Pile

Neuron 1241 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0521. Min Act: -0.0000

Data Index: 252343 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9724. Min Act: -0.0000

Data Index: 597036 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9451. Min Act: -0.0000

Data Index: 376894 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1967550 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9411. Min Act: -0.0000

Data Index: 742495 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9360. Min Act: -0.0000

Data Index: 15657 (The Pile)

Max Activating Token Index: 325

Text #6

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1143194 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1903442 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8562. Min Act: -0.0000

Data Index: 658632 (The Pile)

Max Activating Token Index: 288

Text #9

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1391970 (The Pile)

Max Activating Token Index: 187

Text #10

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1730810 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1624398 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1000443 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8149. Min Act: -0.0000

Data Index: 408416 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8299. Min Act: -0.0000

Data Index: 809569 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8072. Min Act: -0.0000

Data Index: 34548 (The Pile)

Max Activating Token Index: 558

Text #16

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8148. Min Act: -0.0000

Data Index: 648836 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1690141 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8247. Min Act: -0.0000

Data Index: 1593849 (The Pile)

Max Activating Token Index: 521

Text #19

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1920009 (The Pile)

Max Activating Token Index: 916