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

Dataset: The Pile

Neuron 225 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.4070. Min Act: -0.0000

Data Index: 770636 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3540. Min Act: -0.0000

Data Index: 4938 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3556. Min Act: -0.0000

Data Index: 473428 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3604. Min Act: -0.0000

Data Index: 86762 (The Pile)

Max Activating Token Index: 186

Text #4

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3606. Min Act: -0.0000

Data Index: 626495 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3447. Min Act: -0.0000

Data Index: 256434 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3688. Min Act: -0.0000

Data Index: 635414 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1694725 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1762298 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3273. Min Act: -0.0000

Data Index: 690839 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3020. Min Act: -0.0000

Data Index: 369469 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1202184 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3300. Min Act: -0.0000

Data Index: 500792 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3371. Min Act: -0.0000

Data Index: 536279 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3015. Min Act: -0.0000

Data Index: 299302 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3026. Min Act: -0.0000

Data Index: 152094 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1378912 (The Pile)

Max Activating Token Index: 280

Text #17

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2773. Min Act: -0.0000

Data Index: 715910 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2753. Min Act: -0.0000

Data Index: 829412 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1296983 (The Pile)

Max Activating Token Index: 483