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

Dataset: The Pile

Neuron 3058 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: 0.8047. Min Range: -0.8047

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1030754 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7199. Min Act: -0.0000

Data Index: 647446 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7355. Min Act: -0.0000

Data Index: 209314 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1399166 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7149. Min Act: -0.0000

Data Index: 789334 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6951. Min Act: -0.0000

Data Index: 418301 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1441994 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6676. Min Act: -0.0000

Data Index: 235267 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6786. Min Act: -0.0000

Data Index: 231694 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6374. Min Act: -0.0000

Data Index: 590235 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6703. Min Act: -0.0000

Data Index: 1255091 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6765. Min Act: -0.0000

Data Index: 109257 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1497272 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1291464 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1372969 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6209. Min Act: -0.0000

Data Index: 968621 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6434. Min Act: -0.0000

Data Index: 1301147 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1897915 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6512. Min Act: -0.0000

Data Index: 480433 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1522362 (The Pile)

Max Activating Token Index: 872