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

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

Neuron 2405 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5769. Min Act: -0.0000

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1184 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5277. Min Act: -0.0000

Data Index: 252157 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1210376 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4822. Min Act: -0.0000

Data Index: 554733 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4876. Min Act: -0.0000

Data Index: 727468 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1615076 (Python Code)

Max Activating Token Index: 785

Text #7

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1569526 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4428. Min Act: -0.0000

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4248. Min Act: -0.0000

Data Index: 828986 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1468129 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1422938 (Python Code)

Max Activating Token Index: 452

Text #12

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4463. Min Act: -0.0000

Data Index: 216104 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4192. Min Act: -0.0000

Data Index: 582656 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1366501 (Python Code)

Max Activating Token Index: 433

Text #15

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4274. Min Act: -0.0000

Data Index: 749600 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4113. Min Act: -0.0000

Data Index: 932434 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3961. Min Act: -0.0000

Data Index: 574815 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1373286 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1021598 (C4 (Web Text))

Max Activating Token Index: 847