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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 198 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5199. Min Act: -0.0000

Data Index: 896474 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5889. Min Act: -0.0000

Data Index: 940926 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.6389. Min Act: -0.0000

Data Index: 761726 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.6863. Min Act: -0.0000

Data Index: 658589 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.7010. Min Act: -0.0001

Data Index: 22670 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5174. Min Act: -0.0000

Data Index: 523867 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5582. Min Act: -0.0000

Data Index: 30630 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5626. Min Act: -0.0000

Data Index: 52608 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5082. Min Act: -0.0001

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.4887. Min Act: -0.0000

Data Index: 459332 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5314. Min Act: -0.0000

Data Index: 779172 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.6033. Min Act: -0.0000

Data Index: 324260 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5696. Min Act: -0.0000

Data Index: 25372 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.4992. Min Act: -0.0001

Data Index: 934863 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5361. Min Act: -0.0000

Data Index: 916862 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.4433. Min Act: -0.0000

Data Index: 790412 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.4833. Min Act: -0.0000

Data Index: 1076350 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.5490. Min Act: -0.0000

Data Index: 577253 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.4233. Min Act: -0.0000

Data Index: 38500 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 1.7010. Min Range: -1.7010

Max Act: 1.4459. Min Act: -0.0001

Data Index: 334092 (C4 (Web Text))

Max Activating Token Index: 858