Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2165 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.5169. Min Act: -0.0000

Data Index: 346976 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.5450. Min Act: -0.0000

Data Index: 221957 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.5837. Min Act: -0.0000

Data Index: 1980782 (The Pile)

Max Activating Token Index: 148

Text #3

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.5743. Min Act: -0.0000

Data Index: 1849002 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.9712. Min Act: -0.0000

Data Index: 655970 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.5563. Min Act: -0.0000

Data Index: 1675455 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.2993. Min Act: -0.0000

Data Index: 1810969 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.1555. Min Act: -0.0000

Data Index: 1855439 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.2544. Min Act: -0.0000

Data Index: 1473824 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.2217. Min Act: -0.0000

Data Index: 1249514 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.0213. Min Act: -0.0000

Data Index: 1942202 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.0486. Min Act: -0.0000

Data Index: 1535117 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.1830. Min Act: -0.0000

Data Index: 1867861 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.1693. Min Act: -0.0000

Data Index: 30518 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 5.9712. Min Range: -5.9712

Max Act: 4.6047. Min Act: -0.0000

Data Index: 622624 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 5.9712. Min Range: -5.9712

Max Act: 4.9731. Min Act: -0.0000

Data Index: 1683572 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 5.9712. Min Range: -5.9712

Max Act: 4.9738. Min Act: -0.0000

Data Index: 1041694 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 5.9712. Min Range: -5.9712

Max Act: 4.7710. Min Act: -0.0000

Data Index: 1243949 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 5.9712. Min Range: -5.9712

Max Act: 5.3267. Min Act: -0.0000

Data Index: 184726 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 5.9712. Min Range: -5.9712

Max Act: 4.9427. Min Act: -0.0000

Data Index: 1069701 (The Pile)

Max Activating Token Index: 482