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

Dataset: The Pile

Neuron 673 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.8006. Min Act: -0.0000

Data Index: 599307 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7818. Min Act: 0.0000

Data Index: 875922 (The Pile)

Max Activating Token Index: 400

Text #2

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7666. Min Act: -0.0000

Data Index: 66136 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1414494 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1328628 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1104064 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1145392 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6153. Min Act: -0.0000

Data Index: 910125 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1982312 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1707311 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1669815 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5969. Min Act: -0.0000

Data Index: 247445 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1258867 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5730. Min Act: 0.0000

Data Index: 625647 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5547. Min Act: -0.0000

Data Index: 777912 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1903327 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5513. Min Act: -0.0000

Data Index: 61616 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5452. Min Act: -0.0000

Data Index: 857074 (The Pile)

Max Activating Token Index: 926

Text #18

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1287422 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5111. Min Act: -0.0000

Data Index: 929910 (The Pile)

Max Activating Token Index: 460