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

Dataset: The Pile

Neuron 2064 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: 1.4387. Min Range: -1.4387

Max Act: 1.4387. Min Act: -0.0000

Data Index: 1472082 (The Pile)

Max Activating Token Index: 724

Text #1

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.2496. Min Act: -0.0000

Data Index: 1121648 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0791. Min Act: -0.0000

Data Index: 1870936 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1175565 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1817561 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0606. Min Act: -0.0000

Data Index: 119220 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1325354 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 1.4387. Min Range: -1.4387

Max Act: 0.9935. Min Act: -0.0000

Data Index: 457830 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1230774 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1789226 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1389311 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 1.4387. Min Range: -1.4387

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1744459 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0088. Min Act: -0.0000

Data Index: 474463 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1646738 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1605657 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 1.4387. Min Range: -1.4387

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1013505 (The Pile)

Max Activating Token Index: 958

Text #16

Max Range: 1.4387. Min Range: -1.4387

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1022552 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 1.4387. Min Range: -1.4387

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1374578 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 1.4387. Min Range: -1.4387

Max Act: 0.8543. Min Act: -0.0000

Data Index: 141706 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 1.4387. Min Range: -1.4387

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1351851 (The Pile)

Max Activating Token Index: 276