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

Dataset: The Pile

Neuron 4092 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: 0.5080. Min Range: -0.5080

Max Act: 0.5080. Min Act: -0.0000

Data Index: 69391 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4826. Min Act: -0.0000

Data Index: 212505 (The Pile)

Max Activating Token Index: 195

Text #2

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.5060. Min Act: -0.0000

Data Index: 376458 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4676. Min Act: -0.0000

Data Index: 200217 (The Pile)

Max Activating Token Index: 799

Text #4

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1820539 (The Pile)

Max Activating Token Index: 290

Text #5

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4771. Min Act: -0.0000

Data Index: 464160 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4591. Min Act: -0.0000

Data Index: 814850 (The Pile)

Max Activating Token Index: 505

Text #7

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4809. Min Act: -0.0000

Data Index: 705071 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1564535 (The Pile)

Max Activating Token Index: 233

Text #9

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4291. Min Act: -0.0000

Data Index: 858235 (The Pile)

Max Activating Token Index: 563

Text #10

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1603031 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1313136 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1419021 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1273024 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1176024 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3854. Min Act: -0.0000

Data Index: 147357 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3644. Min Act: -0.0000

Data Index: 411239 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1861894 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1645846 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3917. Min Act: -0.0000

Data Index: 258009 (The Pile)

Max Activating Token Index: 887