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

Dataset: The Pile

Neuron 925 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.8177. Min Act: -0.0000

Data Index: 633665 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.7071. Min Act: -0.0000

Data Index: 1782684 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.6858. Min Act: -0.0000

Data Index: 1685107 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.5554. Min Act: -0.0000

Data Index: 1257400 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.4934. Min Act: -0.0000

Data Index: 311576 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1931266 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1158778 (The Pile)

Max Activating Token Index: 556

Text #7

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.6014. Min Act: -0.0000

Data Index: 366778 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.5273. Min Act: -0.0000

Data Index: 155502 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.6098. Min Act: -0.0000

Data Index: 1872913 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.5241. Min Act: -0.0000

Data Index: 322879 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.4799. Min Act: -0.0000

Data Index: 10260 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.4826. Min Act: -0.0000

Data Index: 178384 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.3667. Min Act: -0.0000

Data Index: 486749 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.5392. Min Act: -0.0000

Data Index: 1037333 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.4349. Min Act: -0.0000

Data Index: 1248727 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1034696 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.4265. Min Act: -0.0000

Data Index: 1441092 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.3925. Min Act: -0.0000

Data Index: 72908 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 1.8177. Min Range: -1.8177

Max Act: 1.3556. Min Act: -0.0000

Data Index: 256918 (The Pile)

Max Activating Token Index: 807