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

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

Neuron 1691 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.5382. Min Act: -0.0001

Data Index: 1046403 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4889. Min Act: -0.0001

Data Index: 619906 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4554. Min Act: -0.0001

Data Index: 648645 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4796. Min Act: -0.0001

Data Index: 688844 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4322. Min Act: -0.0001

Data Index: 1196843 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4684. Min Act: -0.0001

Data Index: 414475 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4398. Min Act: -0.0001

Data Index: 1318490 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4663. Min Act: -0.0001

Data Index: 154827 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4322. Min Act: -0.0001

Data Index: 540725 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4696. Min Act: -0.0001

Data Index: 78024 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4502. Min Act: -0.0001

Data Index: 1212117 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4491. Min Act: -0.0001

Data Index: 235795 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4562. Min Act: -0.0001

Data Index: 628021 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4359. Min Act: -0.0001

Data Index: 807719 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4440. Min Act: -0.0001

Data Index: 1226797 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4366. Min Act: -0.0001

Data Index: 767527 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4338. Min Act: -0.0001

Data Index: 291815 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4166. Min Act: -0.0001

Data Index: 377354 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4425. Min Act: -0.0001

Data Index: 424045 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4454. Min Act: -0.0001

Data Index: 290746 (C4 (Web Text))

Max Activating Token Index: 272