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

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

Neuron 3271 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1028387 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3525. Min Act: -0.0000

Data Index: 305624 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3374. Min Act: -0.0000

Data Index: 240607 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1129586 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1355319 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2641. Min Act: -0.0000

Data Index: 281027 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2723. Min Act: -0.0000

Data Index: 9677 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2717. Min Act: -0.0000

Data Index: 245252 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2802. Min Act: -0.0000

Data Index: 781172 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1243786 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2700. Min Act: -0.0000

Data Index: 193458 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2667. Min Act: -0.0000

Data Index: 154438 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1007817 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2710. Min Act: -0.0000

Data Index: 82852 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1223807 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2709. Min Act: -0.0000

Data Index: 629413 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2536. Min Act: -0.0000

Data Index: 2690 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2473. Min Act: -0.0000

Data Index: 244528 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2561. Min Act: -0.0000

Data Index: 839575 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2431. Min Act: -0.0000

Data Index: 578270 (C4 (Web Text))

Max Activating Token Index: 597