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

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

Neuron 1434 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: 1.3770. Min Range: -1.3770

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1056784 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.3770. Min Act: -0.0000

Data Index: 1287759 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.1899. Min Act: -0.0000

Data Index: 935140 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.1837. Min Act: -0.0000

Data Index: 249697 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1124433 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1167476 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.1611. Min Act: -0.0000

Data Index: 78496 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.1574. Min Act: -0.0000

Data Index: 1329174 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.1978. Min Act: -0.0000

Data Index: 432238 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.1165. Min Act: -0.0000

Data Index: 571673 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.0618. Min Act: -0.0000

Data Index: 145998 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1176620 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.0251. Min Act: -0.0000

Data Index: 399654 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 1.3770. Min Range: -1.3770

Max Act: 0.9653. Min Act: -0.0000

Data Index: 240902 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1038415 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.0295. Min Act: -0.0000

Data Index: 250544 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.0356. Min Act: -0.0000

Data Index: 623792 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.0771. Min Act: -0.0000

Data Index: 513116 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1321485 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 1.3770. Min Range: -1.3770

Max Act: 1.0679. Min Act: -0.0000

Data Index: 496104 (C4 (Web Text))

Max Activating Token Index: 379