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

Dataset: The Pile

Neuron 3758 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1665586 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1967466 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1480724 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6514. Min Act: -0.0000

Data Index: 110433 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6897. Min Act: -0.0000

Data Index: 570029 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.7137. Min Act: -0.0000

Data Index: 293087 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1381866 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6535. Min Act: -0.0000

Data Index: 26090 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6266. Min Act: -0.0000

Data Index: 673220 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6112. Min Act: -0.0000

Data Index: 269323 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1982919 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6370. Min Act: -0.0000

Data Index: 477338 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6027. Min Act: -0.0000

Data Index: 389873 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6539. Min Act: -0.0000

Data Index: 550691 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1925981 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1880002 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1122475 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1440750 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1050584 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5694. Min Act: -0.0000

Data Index: 130431 (The Pile)

Max Activating Token Index: 455