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

Dataset: The Pile

Neuron 4109 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: 4.4387. Min Range: -4.4387

Max Act: 4.4387. Min Act: -0.0000

Data Index: 1118541 (The Pile)

Max Activating Token Index: 806

Text #1

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.8280. Min Act: -0.0000

Data Index: 1618989 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.9088. Min Act: -0.0000

Data Index: 1067833 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.0917. Min Act: -0.0000

Data Index: 1210079 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.7307. Min Act: -0.0000

Data Index: 1893736 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.5862. Min Act: -0.0000

Data Index: 1794028 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.4047. Min Act: -0.0000

Data Index: 1351095 (The Pile)

Max Activating Token Index: 931

Text #7

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.4420. Min Act: -0.0000

Data Index: 161321 (The Pile)

Max Activating Token Index: 599

Text #8

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.5999. Min Act: -0.0000

Data Index: 531468 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.3514. Min Act: -0.0000

Data Index: 1722324 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.4628. Min Act: -0.0000

Data Index: 305521 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.6052. Min Act: -0.0000

Data Index: 1404729 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.4295. Min Act: -0.0000

Data Index: 439825 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.2785. Min Act: -0.0000

Data Index: 1503816 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.0683. Min Act: -0.0000

Data Index: 1553260 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.0303. Min Act: -0.0000

Data Index: 1144542 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.4625. Min Act: -0.0000

Data Index: 1153887 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.2350. Min Act: -0.0000

Data Index: 1381000 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 4.4387. Min Range: -4.4387

Max Act: 2.9291. Min Act: -0.0000

Data Index: 1374318 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 4.4387. Min Range: -4.4387

Max Act: 3.2640. Min Act: -0.0000

Data Index: 39006 (The Pile)

Max Activating Token Index: 685