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

Dataset: The Pile

Neuron 241 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1334. Min Act: -0.0000

Data Index: 470795 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1897882 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1074. Min Act: -0.0000

Data Index: 884836 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1011. Min Act: -0.0000

Data Index: 548961 (The Pile)

Max Activating Token Index: 659

Text #4

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1052. Min Act: -0.0000

Data Index: 502478 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1065. Min Act: -0.0000

Data Index: 113784 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1437743 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1391461 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0970. Min Act: -0.0000

Data Index: 917953 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1496219 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0988. Min Act: -0.0000

Data Index: 93678 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1907325 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1372652 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1673936 (The Pile)

Max Activating Token Index: 860

Text #14

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0934. Min Act: -0.0000

Data Index: 343305 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1451473 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0885. Min Act: -0.0000

Data Index: 106054 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1454153 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0985. Min Act: -0.0000

Data Index: 390559 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0831. Min Act: -0.0000

Data Index: 904391 (The Pile)

Max Activating Token Index: 186