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

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

Neuron 5071 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.9352. Min Act: -0.0000

Data Index: 1596895 (Python Code)

Max Activating Token Index: 549

Text #1

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.7924. Min Act: -0.0000

Data Index: 1546592 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.9106. Min Act: -0.0000

Data Index: 1425756 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.7756. Min Act: -0.0000

Data Index: 1581827 (Python Code)

Max Activating Token Index: 518

Text #4

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.7679. Min Act: -0.0000

Data Index: 1371837 (Python Code)

Max Activating Token Index: 408

Text #5

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.7718. Min Act: -0.0000

Data Index: 1420629 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.7277. Min Act: -0.0000

Data Index: 1384355 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.6992. Min Act: -0.0000

Data Index: 1471624 (Python Code)

Max Activating Token Index: 528

Text #8

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.8420. Min Act: -0.0000

Data Index: 1495437 (Python Code)

Max Activating Token Index: 161

Text #9

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.6369. Min Act: -0.0000

Data Index: 1536448 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.6213. Min Act: -0.0000

Data Index: 1419795 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.6140. Min Act: -0.0000

Data Index: 1482652 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.4463. Min Act: -0.0000

Data Index: 1484606 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.7224. Min Act: -0.0000

Data Index: 1512729 (Python Code)

Max Activating Token Index: 155

Text #14

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5560. Min Act: -0.0000

Data Index: 1385150 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5721. Min Act: -0.0000

Data Index: 1497490 (Python Code)

Max Activating Token Index: 290

Text #16

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.4081. Min Act: -0.0000

Data Index: 1441732 (Python Code)

Max Activating Token Index: 467

Text #17

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.6894. Min Act: -0.0000

Data Index: 1453815 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.6882. Min Act: -0.0000

Data Index: 1439563 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5359. Min Act: -0.0000

Data Index: 1645313 (Python Code)

Max Activating Token Index: 831