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

Dataset: The Pile

Neuron 3901 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1371. Min Range: -3.1371

Max Act: 3.1371. Min Act: -0.0000

Data Index: 1603278 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.5910. Min Act: -0.0000

Data Index: 1985784 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.2629. Min Act: -0.0000

Data Index: 1076592 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0893. Min Act: -0.0000

Data Index: 873674 (The Pile)

Max Activating Token Index: 672

Text #4

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.2730. Min Act: -0.0000

Data Index: 665974 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.2057. Min Act: -0.0000

Data Index: 443448 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.3156. Min Act: -0.0000

Data Index: 269328 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.1873. Min Act: -0.0000

Data Index: 1209505 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0305. Min Act: -0.0000

Data Index: 731288 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0147. Min Act: -0.0000

Data Index: 494002 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 3.1371. Min Range: -3.1371

Max Act: 1.9745. Min Act: -0.0000

Data Index: 527718 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.1734. Min Act: -0.0000

Data Index: 1575441 (The Pile)

Max Activating Token Index: 474

Text #12

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0813. Min Act: -0.0000

Data Index: 1976157 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 3.1371. Min Range: -3.1371

Max Act: 1.9922. Min Act: -0.0000

Data Index: 1388387 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0256. Min Act: -0.0000

Data Index: 1518362 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 3.1371. Min Range: -3.1371

Max Act: 1.9243. Min Act: -0.0000

Data Index: 1527891 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0166. Min Act: -0.0000

Data Index: 1124898 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.1268. Min Act: -0.0000

Data Index: 529566 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 3.1371. Min Range: -3.1371

Max Act: 1.9043. Min Act: -0.0000

Data Index: 1471252 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 3.1371. Min Range: -3.1371

Max Act: 2.0053. Min Act: -0.0000

Data Index: 1952008 (The Pile)

Max Activating Token Index: 810