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

Dataset: The Pile

Neuron 3544 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: 3.0182. Min Range: -3.0182

Max Act: 3.0182. Min Act: -0.0000

Data Index: 494197 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.7074. Min Act: -0.0000

Data Index: 1288742 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.8141. Min Act: -0.0000

Data Index: 848943 (The Pile)

Max Activating Token Index: 806

Text #3

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.5963. Min Act: 0.0000

Data Index: 1493419 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.7341. Min Act: -0.0000

Data Index: 1424345 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.4055. Min Act: -0.0000

Data Index: 499456 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.5266. Min Act: 0.0000

Data Index: 1723785 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.4996. Min Act: -0.0000

Data Index: 665459 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.2185. Min Act: 0.0000

Data Index: 1412731 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.2317. Min Act: -0.0000

Data Index: 556733 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.2085. Min Act: -0.0000

Data Index: 368496 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.3414. Min Act: -0.0000

Data Index: 1069802 (The Pile)

Max Activating Token Index: 877

Text #12

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.3089. Min Act: -0.0000

Data Index: 1554563 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.3980. Min Act: 0.0000

Data Index: 1794150 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.1851. Min Act: -0.0000

Data Index: 1200516 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.3806. Min Act: -0.0000

Data Index: 819577 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.2473. Min Act: -0.0000

Data Index: 1013524 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.3716. Min Act: -0.0000

Data Index: 671327 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.1137. Min Act: -0.0000

Data Index: 709664 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 3.0182. Min Range: -3.0182

Max Act: 2.1870. Min Act: 0.0000

Data Index: 957098 (The Pile)

Max Activating Token Index: 429