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

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

Neuron 2483 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1534316 (Python Code)

Max Activating Token Index: 445

Text #1

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1524194 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1491671 (Python Code)

Max Activating Token Index: 964

Text #3

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1414536 (Python Code)

Max Activating Token Index: 581

Text #4

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1360058 (Python Code)

Max Activating Token Index: 758

Text #5

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1363308 (Python Code)

Max Activating Token Index: 849

Text #6

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1592874 (Python Code)

Max Activating Token Index: 525

Text #7

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1510112 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1637591 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1555394 (Python Code)

Max Activating Token Index: 318

Text #10

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1625791 (Python Code)

Max Activating Token Index: 467

Text #11

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1632888 (Python Code)

Max Activating Token Index: 987

Text #12

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1557674 (Python Code)

Max Activating Token Index: 936

Text #13

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.5984. Min Act: -0.0000

Data Index: 110518 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1524409 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1461404 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1498968 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1601412 (Python Code)

Max Activating Token Index: 648

Text #18

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1406691 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.5870. Min Act: -0.0000

Data Index: 673866 (C4 (Web Text))

Max Activating Token Index: 228