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

Dataset: The Pile

Neuron 3672 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1387. Min Act: -0.0000

Data Index: 999595 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1210. Min Act: -0.0000

Data Index: 246015 (The Pile)

Max Activating Token Index: 452

Text #2

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1788715 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1315090 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1061. Min Act: -0.0000

Data Index: 461467 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1096. Min Act: -0.0000

Data Index: 308784 (The Pile)

Max Activating Token Index: 502

Text #6

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1143. Min Act: -0.0000

Data Index: 941981 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1033. Min Act: -0.0000

Data Index: 817022 (The Pile)

Max Activating Token Index: 525

Text #8

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1034. Min Act: -0.0000

Data Index: 374574 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1439043 (The Pile)

Max Activating Token Index: 814

Text #10

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1026. Min Act: -0.0000

Data Index: 305186 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1002. Min Act: -0.0000

Data Index: 699992 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0963. Min Act: -0.0000

Data Index: 195339 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0992. Min Act: -0.0000

Data Index: 496463 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1586962 (The Pile)

Max Activating Token Index: 261

Text #15

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1334627 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1017708 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0908. Min Act: -0.0000

Data Index: 840117 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0922. Min Act: -0.0000

Data Index: 577866 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0858. Min Act: -0.0000

Data Index: 647599 (The Pile)

Max Activating Token Index: 978