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

Dataset: The Pile

Neuron 2669 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.7012. Min Act: -0.0000

Data Index: 672722 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.5584. Min Act: -0.0000

Data Index: 1714614 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1692745 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1167720 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.5357. Min Act: -0.0000

Data Index: 1563916 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1963887 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1653389 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.5533. Min Act: -0.0000

Data Index: 990300 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4689. Min Act: -0.0000

Data Index: 1699011 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1595938 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4612. Min Act: -0.0000

Data Index: 1347084 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1841789 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4506. Min Act: -0.0000

Data Index: 1924530 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4353. Min Act: -0.0000

Data Index: 1037028 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.3649. Min Act: -0.0000

Data Index: 1568002 (The Pile)

Max Activating Token Index: 448

Text #15

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4367. Min Act: -0.0000

Data Index: 1893783 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.3667. Min Act: -0.0000

Data Index: 570290 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4239. Min Act: -0.0000

Data Index: 745187 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.4230. Min Act: -0.0000

Data Index: 348387 (The Pile)

Max Activating Token Index: 167

Text #19

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.3318. Min Act: -0.0000

Data Index: 551802 (The Pile)

Max Activating Token Index: 159