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

Dataset: The Pile

Neuron 3204 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0387. Min Range: -1.0387

Max Act: 1.0387. Min Act: -0.0000

Data Index: 55916 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 1.0387. Min Range: -1.0387

Max Act: 1.0211. Min Act: -0.0000

Data Index: 664955 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 1.0387. Min Range: -1.0387

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1128754 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9088. Min Act: -0.0000

Data Index: 795270 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1520604 (The Pile)

Max Activating Token Index: 409

Text #5

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1219384 (The Pile)

Max Activating Token Index: 936

Text #6

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9559. Min Act: -0.0000

Data Index: 911550 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1265045 (The Pile)

Max Activating Token Index: 381

Text #8

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9778. Min Act: -0.0000

Data Index: 952499 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9247. Min Act: -0.0000

Data Index: 630260 (The Pile)

Max Activating Token Index: 67

Text #10

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1995536 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1106099 (The Pile)

Max Activating Token Index: 545

Text #12

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9106. Min Act: -0.0000

Data Index: 528354 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1241316 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9065. Min Act: -0.0000

Data Index: 765450 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1509056 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1475615 (The Pile)

Max Activating Token Index: 570

Text #17

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1337073 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9120. Min Act: -0.0000

Data Index: 997616 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1004330 (The Pile)

Max Activating Token Index: 829