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

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

Neuron 2037 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: 0.5308. Min Range: -0.5308

Max Act: 0.5308. Min Act: -0.0000

Data Index: 782186 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.5274. Min Act: -0.0000

Data Index: 668291 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4981. Min Act: -0.0000

Data Index: 208342 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4605. Min Act: -0.0000

Data Index: 644383 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4496. Min Act: -0.0000

Data Index: 674466 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4346. Min Act: -0.0000

Data Index: 372310 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4472. Min Act: -0.0000

Data Index: 730815 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1176798 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4285. Min Act: -0.0000

Data Index: 164797 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1173979 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1039941 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1257461 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4185. Min Act: -0.0000

Data Index: 694455 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4203. Min Act: -0.0000

Data Index: 547035 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1342239 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4008. Min Act: -0.0000

Data Index: 796846 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4120. Min Act: -0.0000

Data Index: 642834 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4227. Min Act: -0.0000

Data Index: 693909 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1126826 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.5308. Min Range: -0.5308

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1074014 (C4 (Web Text))

Max Activating Token Index: 458