Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2176 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.5387. Min Act: -0.0000

Data Index: 114636 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.5041. Min Act: -0.0000

Data Index: 57775 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1280688 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4882. Min Act: -0.0000

Data Index: 230783 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1178486 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1895359 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3991. Min Act: -0.0000

Data Index: 944621 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1018982 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1128988 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4172. Min Act: -0.0000

Data Index: 573787 (The Pile)

Max Activating Token Index: 361

Text #10

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1510147 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1189553 (The Pile)

Max Activating Token Index: 160

Text #12

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1754053 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3652. Min Act: -0.0000

Data Index: 958908 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3623. Min Act: -0.0000

Data Index: 369322 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3382. Min Act: -0.0000

Data Index: 572885 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3722. Min Act: -0.0000

Data Index: 387374 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3638. Min Act: -0.0000

Data Index: 128944 (The Pile)

Max Activating Token Index: 785

Text #18

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1796086 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3452. Min Act: 0.0000

Data Index: 1098953 (The Pile)

Max Activating Token Index: 175