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

Dataset: The Pile

Neuron 141 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1977771 (The Pile)

Max Activating Token Index: 543

Text #1

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0886. Min Act: -0.0000

Data Index: 1301577 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.1398. Min Act: -0.0000

Data Index: 537456 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0790. Min Act: -0.0000

Data Index: 590596 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0620. Min Act: -0.0000

Data Index: 966766 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0371. Min Act: -0.0000

Data Index: 672595 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0930. Min Act: -0.0000

Data Index: 326690 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0183. Min Act: -0.0000

Data Index: 870628 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9610. Min Act: -0.0000

Data Index: 559136 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1291861 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1026233 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9115. Min Act: -0.0000

Data Index: 113463 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1968124 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1925553 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8478. Min Act: -0.0000

Data Index: 871299 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8862. Min Act: -0.0000

Data Index: 187002 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1015968 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1914631 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8593. Min Act: -0.0000

Data Index: 109521 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8005. Min Act: -0.0000

Data Index: 957422 (The Pile)

Max Activating Token Index: 172