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

Dataset: The Pile

Neuron 4637 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: 1.5235. Min Range: -1.5235

Max Act: 1.5235. Min Act: -0.0000

Data Index: 1572705 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.4698. Min Act: -0.0000

Data Index: 1727918 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.2244. Min Act: -0.0000

Data Index: 1331523 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1725093 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.1459. Min Act: -0.0000

Data Index: 431083 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.1127. Min Act: -0.0000

Data Index: 398314 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1380875 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 1.5235. Min Range: -1.5235

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1915965 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1336568 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.0159. Min Act: -0.0000

Data Index: 1235122 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.0749. Min Act: -0.0000

Data Index: 1914639 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.0559. Min Act: -0.0000

Data Index: 963172 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 1.5235. Min Range: -1.5235

Max Act: 0.9360. Min Act: -0.0000

Data Index: 106601 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1182682 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 1.5235. Min Range: -1.5235

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1739518 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 1.5235. Min Range: -1.5235

Max Act: 0.9338. Min Act: -0.0000

Data Index: 622350 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 1.5235. Min Range: -1.5235

Max Act: 0.9248. Min Act: -0.0000

Data Index: 825848 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 1.5235. Min Range: -1.5235

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1080267 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 1.5235. Min Range: -1.5235

Max Act: 0.9680. Min Act: -0.0000

Data Index: 183714 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 1.5235. Min Range: -1.5235

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1957481 (The Pile)

Max Activating Token Index: 558