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

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

Neuron 5210 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1910. Min Range: -2.1910

Max Act: 2.1910. Min Act: -0.0000

Data Index: 1604872 (Python Code)

Max Activating Token Index: 523

Text #1

Max Range: 2.1910. Min Range: -2.1910

Max Act: 2.1734. Min Act: -0.0000

Data Index: 623815 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 2.1910. Min Range: -2.1910

Max Act: 2.1261. Min Act: -0.0000

Data Index: 394726 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 2.1910. Min Range: -2.1910

Max Act: 2.0881. Min Act: -0.0000

Data Index: 1449167 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.9469. Min Act: -0.0000

Data Index: 1532166 (Python Code)

Max Activating Token Index: 302

Text #5

Max Range: 2.1910. Min Range: -2.1910

Max Act: 2.0241. Min Act: -0.0000

Data Index: 1459637 (Python Code)

Max Activating Token Index: 179

Text #6

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.9062. Min Act: -0.0000

Data Index: 1536785 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.9892. Min Act: -0.0000

Data Index: 320043 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6953. Min Act: -0.0000

Data Index: 1506647 (Python Code)

Max Activating Token Index: 84

Text #9

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.7777. Min Act: -0.0000

Data Index: 1379492 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.7487. Min Act: -0.0000

Data Index: 1515354 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.7401. Min Act: -0.0000

Data Index: 1510371 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.7317. Min Act: -0.0000

Data Index: 321703 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.8056. Min Act: -0.0000

Data Index: 1625847 (Python Code)

Max Activating Token Index: 329

Text #14

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.7834. Min Act: -0.0000

Data Index: 1648894 (Python Code)

Max Activating Token Index: 885

Text #15

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6287. Min Act: -0.0000

Data Index: 168654 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1496659 (Python Code)

Max Activating Token Index: 480

Text #17

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1538434 (Python Code)

Max Activating Token Index: 190

Text #18

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.5818. Min Act: -0.0000

Data Index: 1618996 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.4826. Min Act: -0.0000

Data Index: 1480406 (Python Code)

Max Activating Token Index: 577