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

Dataset: The Pile

Neuron 3732 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.8160. Min Act: -0.0000

Data Index: 129369 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1114552 (The Pile)

Max Activating Token Index: 322

Text #2

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1402183 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7875. Min Act: -0.0001

Data Index: 64962 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7366. Min Act: -0.0000

Data Index: 317943 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7005. Min Act: -0.0000

Data Index: 428199 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1539858 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1587341 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.6685. Min Act: -0.0000

Data Index: 950327 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.6625. Min Act: -0.0000

Data Index: 132275 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1975380 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1533701 (The Pile)

Max Activating Token Index: 357

Text #12

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.5736. Min Act: -0.0000

Data Index: 923400 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1827630 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.4867. Min Act: -0.0000

Data Index: 51192 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.5356. Min Act: -0.0000

Data Index: 526554 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.5798. Min Act: -0.0000

Data Index: 863013 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1669660 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1720245 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.5811. Min Act: -0.0000

Data Index: 339885 (The Pile)

Max Activating Token Index: 809