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

Dataset: The Pile

Neuron 757 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1990317 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.7378. Min Act: -0.0000

Data Index: 918627 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1620677 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6144. Min Act: -0.0000

Data Index: 329923 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1500094 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1323581 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1719695 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1019476 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1998342 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5689. Min Act: -0.0000

Data Index: 313411 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6057. Min Act: -0.0000

Data Index: 407544 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1051419 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5620. Min Act: -0.0000

Data Index: 50708 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1144716 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1570537 (The Pile)

Max Activating Token Index: 766

Text #15

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5850. Min Act: -0.0000

Data Index: 181271 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5438. Min Act: -0.0000

Data Index: 180516 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6043. Min Act: -0.0000

Data Index: 443785 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1113746 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1146582 (The Pile)

Max Activating Token Index: 368