Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1917 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0406. Min Act: -0.0001

Data Index: 230401 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0000

Data Index: 454136 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0390. Min Act: -0.0001

Data Index: 774832 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0326. Min Act: -0.0000

Data Index: 244851 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1086438 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0324. Min Act: -0.0001

Data Index: 342605 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0353. Min Act: -0.0001

Data Index: 60555 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0327. Min Act: -0.0001

Data Index: 233409 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1198050 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0317. Min Act: -0.0001

Data Index: 818559 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1290396 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1010412 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1337107 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0284. Min Act: -0.0001

Data Index: 614815 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0307. Min Act: -0.0001

Data Index: 536748 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0269. Min Act: -0.0001

Data Index: 833811 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0283. Min Act: -0.0000

Data Index: 11695 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0235. Min Act: -0.0001

Data Index: 276828 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1511284 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0277. Min Act: -0.0001

Data Index: 301250 (C4 (Web Text))

Max Activating Token Index: 732