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

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

Neuron 2306 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0003

Data Index: 255417 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0580. Min Act: -0.0004

Data Index: 350649 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0561. Min Act: -0.0003

Data Index: 229608 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1348910 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1336820 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1178820 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0414. Min Act: -0.0003

Data Index: 675819 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0411. Min Act: -0.0003

Data Index: 793120 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0391. Min Act: -0.0003

Data Index: 375941 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1127973 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0400. Min Act: -0.0003

Data Index: 659999 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1162678 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0395. Min Act: -0.0003

Data Index: 77423 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0361. Min Act: -0.0003

Data Index: 970495 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0373. Min Act: -0.0004

Data Index: 1165601 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1295531 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0384. Min Act: -0.0003

Data Index: 899895 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0341. Min Act: -0.0003

Data Index: 930706 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0368. Min Act: -0.0003

Data Index: 946610 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0365. Min Act: -0.0003

Data Index: 895592 (C4 (Web Text))

Max Activating Token Index: 616