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

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

Neuron 939 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4704. Min Range: -2.4704

Max Act: 2.4704. Min Act: 0.0000

Data Index: 1530921 (Python Code)

Max Activating Token Index: 163

Text #1

Max Range: 2.4704. Min Range: -2.4704

Max Act: 2.4329. Min Act: 0.0000

Data Index: 1525440 (Python Code)

Max Activating Token Index: 665

Text #2

Max Range: 2.4704. Min Range: -2.4704

Max Act: 2.3870. Min Act: 0.0000

Data Index: 1514839 (Python Code)

Max Activating Token Index: 930

Text #3

Max Range: 2.4704. Min Range: -2.4704

Max Act: 2.2614. Min Act: 0.0000

Data Index: 1581826 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.9669. Min Act: 0.0000

Data Index: 1602937 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.9252. Min Act: 0.0000

Data Index: 1635061 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.7679. Min Act: 0.0000

Data Index: 1429963 (Python Code)

Max Activating Token Index: 352

Text #7

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.8521. Min Act: 0.0000

Data Index: 1602468 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.7424. Min Act: 0.0000

Data Index: 1569409 (Python Code)

Max Activating Token Index: 996

Text #9

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.6983. Min Act: 0.0000

Data Index: 1500964 (Python Code)

Max Activating Token Index: 799

Text #10

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.6910. Min Act: 0.0000

Data Index: 1364928 (Python Code)

Max Activating Token Index: 828

Text #11

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.5484. Min Act: -0.0000

Data Index: 1482193 (Python Code)

Max Activating Token Index: 813

Text #12

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.5238. Min Act: 0.0000

Data Index: 1654050 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.5988. Min Act: 0.0000

Data Index: 1439718 (Python Code)

Max Activating Token Index: 198

Text #14

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.5213. Min Act: 0.0000

Data Index: 1623530 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.6802. Min Act: 0.0000

Data Index: 1450440 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.4795. Min Act: -0.0000

Data Index: 1452212 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.3841. Min Act: 0.0000

Data Index: 1447283 (Python Code)

Max Activating Token Index: 77

Text #18

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.5583. Min Act: 0.0000

Data Index: 1615702 (Python Code)

Max Activating Token Index: 506

Text #19

Max Range: 2.4704. Min Range: -2.4704

Max Act: 1.5443. Min Act: 0.0000

Data Index: 1606610 (Python Code)

Max Activating Token Index: 429