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

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

Neuron 1360 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: 2.1492. Min Range: -2.1492

Max Act: 2.1492. Min Act: -0.0000

Data Index: 1365049 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.9860. Min Act: 0.0000

Data Index: 1468487 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.9173. Min Act: -0.0000

Data Index: 1563325 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.7428. Min Act: -0.0000

Data Index: 1571970 (Python Code)

Max Activating Token Index: 608

Text #4

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.5513. Min Act: -0.0000

Data Index: 1391863 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.5081. Min Act: -0.0000

Data Index: 1364005 (Python Code)

Max Activating Token Index: 537

Text #6

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.4934. Min Act: -0.0000

Data Index: 1601104 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.4368. Min Act: -0.0000

Data Index: 1442188 (Python Code)

Max Activating Token Index: 128

Text #8

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.3317. Min Act: -0.0000

Data Index: 1531716 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1386706 (Python Code)

Max Activating Token Index: 658

Text #10

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1417917 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1400448 (Python Code)

Max Activating Token Index: 792

Text #12

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.4170. Min Act: -0.0000

Data Index: 1545517 (Python Code)

Max Activating Token Index: 1007

Text #13

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1464233 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.3033. Min Act: -0.0000

Data Index: 1533409 (Python Code)

Max Activating Token Index: 593

Text #15

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1440672 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.3656. Min Act: -0.0000

Data Index: 1427537 (Python Code)

Max Activating Token Index: 271

Text #17

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1640395 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1496723 (Python Code)

Max Activating Token Index: 328

Text #19

Max Range: 2.1492. Min Range: -2.1492

Max Act: 1.2611. Min Act: -0.0000

Data Index: 1490090 (Python Code)

Max Activating Token Index: 56