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

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

Neuron 2318 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0553. Min Act: -0.0000

Data Index: 170667 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0561. Min Act: -0.0000

Data Index: 392653 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0000

Data Index: 28634 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1062263 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0493. Min Act: -0.0000

Data Index: 83157 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0508. Min Act: -0.0000

Data Index: 715005 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1251015 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0484. Min Act: -0.0000

Data Index: 1220654 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0453. Min Act: -0.0000

Data Index: 24780 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0457. Min Act: -0.0000

Data Index: 369402 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0431. Min Act: -0.0000

Data Index: 192103 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1037577 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0460. Min Act: -0.0000

Data Index: 412584 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1129312 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0414. Min Act: -0.0000

Data Index: 650858 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0430. Min Act: -0.0000

Data Index: 887881 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0424. Min Act: -0.0000

Data Index: 819456 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0438. Min Act: -0.0000

Data Index: 878377 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1119745 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0396. Min Act: -0.0000

Data Index: 58318 (C4 (Web Text))

Max Activating Token Index: 287