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

Dataset: The Pile

Neuron 4347 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: 1.8074. Min Range: -1.8074

Max Act: 1.4805. Min Act: -0.0000

Data Index: 597249 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.5022. Min Act: -0.0000

Data Index: 620824 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.8074. Min Act: -0.0000

Data Index: 644736 (The Pile)

Max Activating Token Index: 451

Text #3

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.4559. Min Act: -0.0000

Data Index: 1316847 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.6778. Min Act: -0.0000

Data Index: 1180270 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.4006. Min Act: -0.0000

Data Index: 1248908 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.5376. Min Act: -0.0000

Data Index: 77992 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.5734. Min Act: -0.0000

Data Index: 1885954 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.4088. Min Act: -0.0000

Data Index: 1254847 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.3642. Min Act: -0.0000

Data Index: 277836 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.3390. Min Act: -0.0000

Data Index: 529303 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.5068. Min Act: -0.0000

Data Index: 478706 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.6369. Min Act: -0.0000

Data Index: 329179 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.4637. Min Act: -0.0000

Data Index: 732897 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.4747. Min Act: -0.0000

Data Index: 1312224 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1458917 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.5681. Min Act: -0.0000

Data Index: 611087 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.2383. Min Act: -0.0000

Data Index: 28264 (The Pile)

Max Activating Token Index: 383

Text #18

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1252610 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 1.8074. Min Range: -1.8074

Max Act: 1.3087. Min Act: -0.0000

Data Index: 1544753 (The Pile)

Max Activating Token Index: 243