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

Dataset: The Pile

Neuron 4526 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: 3.4234. Min Range: -3.4234

Max Act: 3.4234. Min Act: -0.0000

Data Index: 206152 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.4099. Min Act: -0.0000

Data Index: 1414165 (The Pile)

Max Activating Token Index: 64

Text #2

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2597. Min Act: -0.0000

Data Index: 717976 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.0669. Min Act: -0.0000

Data Index: 818885 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2117. Min Act: -0.0000

Data Index: 1842839 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.0777. Min Act: -0.0000

Data Index: 42384 (The Pile)

Max Activating Token Index: 538

Text #6

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.0637. Min Act: -0.0000

Data Index: 1775463 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.0053. Min Act: -0.0000

Data Index: 866766 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.8000. Min Act: -0.0000

Data Index: 1239731 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.7350. Min Act: -0.0000

Data Index: 826275 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.8645. Min Act: -0.0000

Data Index: 31806 (The Pile)

Max Activating Token Index: 980

Text #11

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.8590. Min Act: -0.0000

Data Index: 1671917 (The Pile)

Max Activating Token Index: 649

Text #12

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.8255. Min Act: -0.0000

Data Index: 298595 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.7961. Min Act: -0.0000

Data Index: 1122770 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.7930. Min Act: -0.0000

Data Index: 627464 (The Pile)

Max Activating Token Index: 444

Text #15

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.5883. Min Act: -0.0000

Data Index: 259682 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.7147. Min Act: -0.0000

Data Index: 980856 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.6808. Min Act: -0.0000

Data Index: 338746 (The Pile)

Max Activating Token Index: 647

Text #18

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.5086. Min Act: -0.0000

Data Index: 1863620 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 3.4234. Min Range: -3.4234

Max Act: 2.6555. Min Act: -0.0000

Data Index: 1348269 (The Pile)

Max Activating Token Index: 340