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

Dataset: The Pile

Neuron 2468 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: 1.3571. Min Range: -1.3571

Max Act: 1.3571. Min Act: -0.0000

Data Index: 963550 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 1.3571. Min Range: -1.3571

Max Act: 1.0886. Min Act: -0.0000

Data Index: 1447212 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.9095. Min Act: -0.0000

Data Index: 185760 (The Pile)

Max Activating Token Index: 858

Text #3

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1880129 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1402900 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1664957 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1602958 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1123110 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1968057 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.8533. Min Act: -0.0000

Data Index: 452856 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1033186 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1698212 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1136410 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1431414 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1960550 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.7028. Min Act: -0.0000

Data Index: 340909 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.7021. Min Act: -0.0000

Data Index: 819542 (The Pile)

Max Activating Token Index: 417

Text #17

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1724126 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1615537 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 1.3571. Min Range: -1.3571

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1115450 (The Pile)

Max Activating Token Index: 627