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

Dataset: The Pile

Neuron 735 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: 1.6674. Min Range: -1.6674

Max Act: 1.6674. Min Act: -0.0000

Data Index: 182990 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4858. Min Act: -0.0000

Data Index: 1888321 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4865. Min Act: -0.0000

Data Index: 15391 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1212389 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1854145 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1663296 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4832. Min Act: -0.0000

Data Index: 738887 (The Pile)

Max Activating Token Index: 262

Text #7

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4184. Min Act: -0.0000

Data Index: 130463 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1874575 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1917895 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4358. Min Act: -0.0000

Data Index: 225626 (The Pile)

Max Activating Token Index: 672

Text #11

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4448. Min Act: -0.0000

Data Index: 250764 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1718988 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4282. Min Act: -0.0000

Data Index: 1321980 (The Pile)

Max Activating Token Index: 429

Text #14

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4194. Min Act: -0.0000

Data Index: 1309434 (The Pile)

Max Activating Token Index: 844

Text #15

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3745. Min Act: -0.0000

Data Index: 1607192 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3474. Min Act: -0.0000

Data Index: 1926035 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4931. Min Act: -0.0000

Data Index: 16298 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3283. Min Act: -0.0000

Data Index: 1316791 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4837. Min Act: -0.0000

Data Index: 1516824 (The Pile)

Max Activating Token Index: 741