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

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

Neuron 2390 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: 0.7893. Min Range: -0.7893

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1143705 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1160213 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1239041 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1189186 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.5118. Min Act: -0.0000

Data Index: 10962 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4640. Min Act: -0.0000

Data Index: 144433 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4877. Min Act: -0.0000

Data Index: 404748 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4625. Min Act: -0.0000

Data Index: 137356 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4476. Min Act: -0.0000

Data Index: 273031 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4922. Min Act: -0.0000

Data Index: 916699 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.5086. Min Act: -0.0000

Data Index: 155933 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4217. Min Act: -0.0000

Data Index: 849553 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4470. Min Act: -0.0000

Data Index: 930513 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4545. Min Act: -0.0000

Data Index: 555585 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4411. Min Act: -0.0000

Data Index: 164863 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4550. Min Act: -0.0000

Data Index: 675353 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4611. Min Act: -0.0000

Data Index: 777526 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4416. Min Act: -0.0000

Data Index: 946896 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4376. Min Act: -0.0000

Data Index: 339187 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.4504. Min Act: -0.0000

Data Index: 72824 (C4 (Web Text))

Max Activating Token Index: 879