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

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

Neuron 1465 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0261. Min Act: -0.0000

Data Index: 35770 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0447. Min Act: -0.0000

Data Index: 455521 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1046430 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1340977 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9590. Min Act: -0.0000

Data Index: 527859 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0446. Min Act: -0.0000

Data Index: 936805 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0143. Min Act: -0.0000

Data Index: 460990 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0008. Min Act: -0.0000

Data Index: 326997 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1447955 (Python Code)

Max Activating Token Index: 828

Text #9

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1309870 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9380. Min Act: -0.0000

Data Index: 733432 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9366. Min Act: -0.0000

Data Index: 32093 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9377. Min Act: -0.0000

Data Index: 547949 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1494693 (Python Code)

Max Activating Token Index: 736

Text #14

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1124007 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9254. Min Act: -0.0000

Data Index: 80619 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1574215 (Python Code)

Max Activating Token Index: 479

Text #17

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9175. Min Act: -0.0000

Data Index: 411758 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9490. Min Act: -0.0000

Data Index: 148633 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1448879 (Python Code)

Max Activating Token Index: 518