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

Dataset: The Pile

Neuron 1732 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: 0.7270. Min Act: -0.0000

Data Index: 268803 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1678295 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1655061 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6970. Min Act: -0.0000

Data Index: 506687 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1993293 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6623. Min Act: -0.0000

Data Index: 438008 (The Pile)

Max Activating Token Index: 727

Text #6

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1234014 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6426. Min Act: -0.0000

Data Index: 508026 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1850614 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6192. Min Act: -0.0000

Data Index: 687123 (The Pile)

Max Activating Token Index: 469

Text #10

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1279321 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5928. Min Act: -0.0000

Data Index: 442056 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1141013 (The Pile)

Max Activating Token Index: 253

Text #13

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1961087 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1320393 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5755. Min Act: -0.0000

Data Index: 869149 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5594. Min Act: -0.0000

Data Index: 414407 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1509192 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1329749 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1577447 (The Pile)

Max Activating Token Index: 9