Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4765 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3473. Min Range: -2.3473

Max Act: 2.3473. Min Act: -0.0000

Data Index: 195766 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 2.3473. Min Range: -2.3473

Max Act: 2.2517. Min Act: -0.0000

Data Index: 716804 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 2.3473. Min Range: -2.3473

Max Act: 1.6672. Min Act: -0.0000

Data Index: 555771 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 2.3473. Min Range: -2.3473

Max Act: 1.1791. Min Act: -0.0000

Data Index: 301047 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 2.3473. Min Range: -2.3473

Max Act: 1.0030. Min Act: -0.0000

Data Index: 110337 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.9003. Min Act: -0.0000

Data Index: 13388 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1060416 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.3401. Min Act: -0.0000

Data Index: 931806 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.2701. Min Act: -0.0000

Data Index: 261565 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1492536 (Python Code)

Max Activating Token Index: 380

Text #10

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1204397 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.1517. Min Act: -0.0000

Data Index: 788807 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.1698. Min Act: -0.0000

Data Index: 56181 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1119476 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.1746. Min Act: -0.0000

Data Index: 426730 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1311886 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.1635. Min Act: -0.0000

Data Index: 896919 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.1561. Min Act: -0.0000

Data Index: 279905 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1003101 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 2.3473. Min Range: -2.3473

Max Act: 0.1589. Min Act: -0.0000

Data Index: 717227 (C4 (Web Text))

Max Activating Token Index: 721