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

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

Neuron 3908 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: 0.5238. Min Range: -0.5238

Max Act: 0.5238. Min Act: -0.0000

Data Index: 665089 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4893. Min Act: -0.0000

Data Index: 450921 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1195654 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1254404 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4104. Min Act: -0.0000

Data Index: 843574 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3799. Min Act: -0.0000

Data Index: 364691 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4017. Min Act: -0.0000

Data Index: 731199 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4097. Min Act: -0.0000

Data Index: 621100 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1184869 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3525. Min Act: -0.0000

Data Index: 493330 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3670. Min Act: -0.0000

Data Index: 779804 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1335357 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1064914 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1189611 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3639. Min Act: -0.0000

Data Index: 812278 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1050851 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3593. Min Act: -0.0000

Data Index: 25893 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1196928 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1211775 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.3579. Min Act: -0.0000

Data Index: 72483 (C4 (Web Text))

Max Activating Token Index: 290