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

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

Neuron 2183 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1492897 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1611504 (Python Code)

Max Activating Token Index: 681

Text #2

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1473146 (Python Code)

Max Activating Token Index: 69

Text #3

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1488397 (Python Code)

Max Activating Token Index: 569

Text #4

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1611981 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1556638 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1515537 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1373919 (Python Code)

Max Activating Token Index: 779

Text #8

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1521111 (Python Code)

Max Activating Token Index: 380

Text #9

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1573712 (Python Code)

Max Activating Token Index: 639

Text #10

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1505704 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1595108 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1459926 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1491461 (Python Code)

Max Activating Token Index: 852

Text #14

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1399240 (Python Code)

Max Activating Token Index: 691

Text #15

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1644261 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1371393 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1514817 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1518819 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1534459 (Python Code)

Max Activating Token Index: 347