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

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

Neuron 4643 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: 4.3005. Min Range: -4.3005

Max Act: 4.3005. Min Act: -0.0000

Data Index: 1575331 (Python Code)

Max Activating Token Index: 669

Text #1

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1135. Min Act: -0.0000

Data Index: 1596857 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.9523. Min Act: -0.0000

Data Index: 1608603 (Python Code)

Max Activating Token Index: 803

Text #3

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.2812. Min Act: -0.0000

Data Index: 1568219 (Python Code)

Max Activating Token Index: 568

Text #4

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.8173. Min Act: -0.0000

Data Index: 1390321 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.0018. Min Act: -0.0000

Data Index: 1374781 (Python Code)

Max Activating Token Index: 507

Text #6

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.8252. Min Act: -0.0000

Data Index: 1490392 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.9364. Min Act: -0.0000

Data Index: 1441446 (Python Code)

Max Activating Token Index: 89

Text #8

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.9176. Min Act: -0.0000

Data Index: 1553026 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.8873. Min Act: -0.0000

Data Index: 1384141 (Python Code)

Max Activating Token Index: 604

Text #10

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.0407. Min Act: -0.0000

Data Index: 1574193 (Python Code)

Max Activating Token Index: 274

Text #11

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.6791. Min Act: -0.0000

Data Index: 1377963 (Python Code)

Max Activating Token Index: 585

Text #12

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.6856. Min Act: -0.0000

Data Index: 1649986 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.8022. Min Act: -0.0000

Data Index: 1449578 (Python Code)

Max Activating Token Index: 507

Text #14

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.7703. Min Act: -0.0000

Data Index: 1568568 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.0713. Min Act: -0.0000

Data Index: 1435209 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.7366. Min Act: -0.0000

Data Index: 1564251 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.5540. Min Act: -0.0000

Data Index: 1476253 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.5346. Min Act: -0.0000

Data Index: 1509555 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 4.3005. Min Range: -4.3005

Max Act: 3.8405. Min Act: -0.0000

Data Index: 1462652 (Python Code)

Max Activating Token Index: 715