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

Dataset: The Pile

Neuron 3140 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: 1.2762. Min Range: -1.2762

Max Act: 1.2762. Min Act: -0.0000

Data Index: 41722 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.2387. Min Act: -0.0000

Data Index: 637753 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.1781. Min Act: -0.0000

Data Index: 692015 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1755163 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1750480 (The Pile)

Max Activating Token Index: 785

Text #5

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8617. Min Act: -0.0000

Data Index: 443194 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1811363 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8534. Min Act: -0.0000

Data Index: 969857 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8745. Min Act: -0.0000

Data Index: 870410 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1624008 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8420. Min Act: -0.0000

Data Index: 1402886 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1445257 (The Pile)

Max Activating Token Index: 871

Text #12

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8629. Min Act: -0.0000

Data Index: 904334 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8272. Min Act: -0.0000

Data Index: 138898 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.7738. Min Act: -0.0000

Data Index: 72593 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8464. Min Act: -0.0000

Data Index: 834454 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1735391 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.7861. Min Act: -0.0000

Data Index: 369645 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1978354 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1989079 (The Pile)

Max Activating Token Index: 522