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

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

Neuron 3809 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: 0.6362. Min Range: -0.6362

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1173088 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1292412 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1354633 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5822. Min Act: -0.0000

Data Index: 111184 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5490. Min Act: -0.0000

Data Index: 822087 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5789. Min Act: -0.0000

Data Index: 672539 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5179. Min Act: -0.0000

Data Index: 951382 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.6362. Min Act: -0.0000

Data Index: 649558 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5105. Min Act: -0.0000

Data Index: 981493 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5330. Min Act: -0.0000

Data Index: 448271 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.3387. Min Act: -0.0000

Data Index: 409216 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.3523. Min Act: -0.0000

Data Index: 588705 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.3812. Min Act: -0.0000

Data Index: 743220 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4088. Min Act: -0.0000

Data Index: 825462 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.3207. Min Act: -0.0000

Data Index: 565400 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1222660 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.3349. Min Act: -0.0000

Data Index: 113835 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1312638 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1223088 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.3374. Min Act: -0.0000

Data Index: 459028 (C4 (Web Text))

Max Activating Token Index: 554