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

Dataset: The Pile

Neuron 2947 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: 1.8322. Min Range: -1.8322

Max Act: 1.8322. Min Act: -0.0000

Data Index: 279683 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1504596 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.5491. Min Act: -0.0000

Data Index: 846187 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.5600. Min Act: -0.0000

Data Index: 922386 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1517367 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.4593. Min Act: -0.0000

Data Index: 25946 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.6305. Min Act: -0.0000

Data Index: 1915977 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.3552. Min Act: -0.0000

Data Index: 1342740 (The Pile)

Max Activating Token Index: 525

Text #8

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.4694. Min Act: -0.0000

Data Index: 1307423 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1442287 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.4390. Min Act: -0.0000

Data Index: 1685517 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.3329. Min Act: -0.0000

Data Index: 1514226 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.3619. Min Act: -0.0000

Data Index: 51576 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.2966. Min Act: -0.0000

Data Index: 684531 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.2686. Min Act: -0.0000

Data Index: 15293 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.3751. Min Act: -0.0000

Data Index: 1203837 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.3275. Min Act: -0.0000

Data Index: 373678 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1716339 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.5459. Min Act: -0.0000

Data Index: 172022 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.2092. Min Act: -0.0000

Data Index: 349927 (The Pile)

Max Activating Token Index: 554