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

Dataset: The Pile

Neuron 3323 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2697. Min Act: -0.0000

Data Index: 874878 (The Pile)

Max Activating Token Index: 849

Text #1

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1445491 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1280869 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2348. Min Act: -0.0000

Data Index: 204440 (The Pile)

Max Activating Token Index: 641

Text #4

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1932782 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2177. Min Act: -0.0000

Data Index: 23326 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2289. Min Act: -0.0000

Data Index: 382802 (The Pile)

Max Activating Token Index: 720

Text #7

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1507024 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2076. Min Act: -0.0000

Data Index: 329117 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2157. Min Act: -0.0000

Data Index: 241372 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2052. Min Act: -0.0000

Data Index: 867373 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2045. Min Act: -0.0000

Data Index: 31607 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1246426 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1343347 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2040. Min Act: -0.0000

Data Index: 92429 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1288116 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1972. Min Act: -0.0000

Data Index: 37086 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1965. Min Act: -0.0000

Data Index: 712227 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1938. Min Act: -0.0000

Data Index: 551564 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1131310 (The Pile)

Max Activating Token Index: 384