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

Dataset: The Pile

Neuron 2806 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5220. Min Act: -0.0000

Data Index: 546470 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1317654 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1750290 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1155758 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1491714 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4854. Min Act: -0.0000

Data Index: 949356 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1302814 (The Pile)

Max Activating Token Index: 892

Text #7

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4170. Min Act: -0.0000

Data Index: 385580 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4307. Min Act: -0.0000

Data Index: 601455 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4781. Min Act: -0.0000

Data Index: 17575 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1584305 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4318. Min Act: -0.0000

Data Index: 328424 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1524006 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4270. Min Act: -0.0000

Data Index: 855407 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1980509 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3959. Min Act: -0.0000

Data Index: 625977 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4056. Min Act: -0.0000

Data Index: 108543 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1270092 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4506. Min Act: -0.0000

Data Index: 553344 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4238. Min Act: -0.0000

Data Index: 517323 (The Pile)

Max Activating Token Index: 27