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

Dataset: The Pile

Neuron 2327 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: 1.6634. Min Range: -1.6634

Max Act: 1.5187. Min Act: -0.0000

Data Index: 765430 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.6634. Min Act: -0.0000

Data Index: 1215811 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.6522. Min Act: -0.0000

Data Index: 1814075 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.5445. Min Act: -0.0000

Data Index: 24377 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.5552. Min Act: -0.0000

Data Index: 1434106 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.5179. Min Act: -0.0000

Data Index: 923032 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.4190. Min Act: -0.0000

Data Index: 974388 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.4848. Min Act: -0.0000

Data Index: 770287 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3124. Min Act: -0.0000

Data Index: 343111 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1491305 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3748. Min Act: -0.0000

Data Index: 1547914 (The Pile)

Max Activating Token Index: 787

Text #11

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3647. Min Act: -0.0000

Data Index: 1947439 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3652. Min Act: -0.0000

Data Index: 1701741 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.1917. Min Act: -0.0000

Data Index: 346597 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1961387 (The Pile)

Max Activating Token Index: 692

Text #15

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3820. Min Act: -0.0000

Data Index: 1020274 (The Pile)

Max Activating Token Index: 840

Text #16

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3499. Min Act: -0.0000

Data Index: 81380 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.2677. Min Act: -0.0000

Data Index: 583176 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1737603 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.1948. Min Act: -0.0000

Data Index: 140345 (The Pile)

Max Activating Token Index: 972