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

Dataset: The Pile

Neuron 846 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1595976 (The Pile)

Max Activating Token Index: 806

Text #1

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1279942 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1257538 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1204425 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1925301 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6175. Min Act: -0.0000

Data Index: 785992 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6362. Min Act: 0.0000

Data Index: 894476 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6281. Min Act: -0.0000

Data Index: 76030 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1844930 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5975. Min Act: -0.0000

Data Index: 433195 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1259402 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5636. Min Act: -0.0000

Data Index: 607971 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5330. Min Act: -0.0000

Data Index: 284367 (The Pile)

Max Activating Token Index: 348

Text #13

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5965. Min Act: 0.0001

Data Index: 898213 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1632675 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5083. Min Act: -0.0000

Data Index: 623874 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1816174 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5193. Min Act: -0.0000

Data Index: 612030 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5313. Min Act: -0.0000

Data Index: 904916 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1998140 (The Pile)

Max Activating Token Index: 249