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

Dataset: The Pile

Neuron 151 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: 1.7370. Min Range: -1.7370

Max Act: 1.7370. Min Act: -0.0000

Data Index: 197718 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.6918. Min Act: -0.0000

Data Index: 715669 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.5478. Min Act: -0.0000

Data Index: 46118 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.5276. Min Act: -0.0000

Data Index: 788261 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1374029 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.5258. Min Act: -0.0000

Data Index: 1158660 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.7144. Min Act: -0.0000

Data Index: 484423 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1299773 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.4366. Min Act: -0.0000

Data Index: 872855 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1423488 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.5933. Min Act: -0.0000

Data Index: 1001907 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.3089. Min Act: -0.0000

Data Index: 1950312 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.2824. Min Act: -0.0000

Data Index: 628850 (The Pile)

Max Activating Token Index: 762

Text #13

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.3467. Min Act: -0.0000

Data Index: 1253684 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1985303 (The Pile)

Max Activating Token Index: 648

Text #15

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1112805 (The Pile)

Max Activating Token Index: 66

Text #16

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1961863 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1297380 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.2866. Min Act: -0.0000

Data Index: 653736 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 1.7370. Min Range: -1.7370

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1248844 (The Pile)

Max Activating Token Index: 88