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

Dataset: The Pile

Neuron 3941 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: 1.7283. Min Range: -1.7283

Max Act: 1.7283. Min Act: -0.0000

Data Index: 261997 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1435925 (The Pile)

Max Activating Token Index: 731

Text #2

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5083. Min Act: -0.0000

Data Index: 1775049 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.6657. Min Act: -0.0000

Data Index: 1900277 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5635. Min Act: -0.0000

Data Index: 1039074 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1600743 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.6014. Min Act: -0.0000

Data Index: 115813 (The Pile)

Max Activating Token Index: 220

Text #7

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5357. Min Act: -0.0000

Data Index: 1904053 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5392. Min Act: -0.0000

Data Index: 624737 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4916. Min Act: -0.0000

Data Index: 671615 (The Pile)

Max Activating Token Index: 200

Text #10

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5265. Min Act: -0.0000

Data Index: 1278269 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5153. Min Act: -0.0000

Data Index: 484681 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1342667 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.6003. Min Act: -0.0000

Data Index: 1976111 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4856. Min Act: -0.0000

Data Index: 151056 (The Pile)

Max Activating Token Index: 181

Text #15

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5166. Min Act: -0.0000

Data Index: 400993 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4684. Min Act: -0.0000

Data Index: 1229772 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3908. Min Act: -0.0000

Data Index: 1470332 (The Pile)

Max Activating Token Index: 563

Text #18

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3974. Min Act: -0.0000

Data Index: 1886149 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4798. Min Act: -0.0000

Data Index: 232583 (The Pile)

Max Activating Token Index: 70