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

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

Neuron 495 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2233. Min Act: -0.0000

Data Index: 635818 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2015. Min Act: -0.0000

Data Index: 881852 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1106558 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1319441 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1293484 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1501. Min Act: -0.0000

Data Index: 175019 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1575. Min Act: -0.0000

Data Index: 397617 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1631. Min Act: -0.0000

Data Index: 150632 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1521. Min Act: -0.0000

Data Index: 465503 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1079416 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1151833 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1444. Min Act: -0.0000

Data Index: 713494 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1364. Min Act: -0.0000

Data Index: 909259 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1401. Min Act: -0.0000

Data Index: 801296 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1011094 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1339. Min Act: 0.0000

Data Index: 664747 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1274. Min Act: -0.0000

Data Index: 672879 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1276. Min Act: -0.0000

Data Index: 863865 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1281. Min Act: -0.0000

Data Index: 762922 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1231. Min Act: -0.0000

Data Index: 361482 (C4 (Web Text))

Max Activating Token Index: 634