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

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

Neuron 73 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2717. Min Range: -2.2717

Max Act: 2.2717. Min Act: -0.0000

Data Index: 1513924 (Python Code)

Max Activating Token Index: 727

Text #1

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9105. Min Act: -0.0000

Data Index: 1583069 (Python Code)

Max Activating Token Index: 224

Text #2

Max Range: 2.2717. Min Range: -2.2717

Max Act: 2.0383. Min Act: -0.0000

Data Index: 1602879 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8094. Min Act: -0.0000

Data Index: 1561432 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.7511. Min Act: -0.0000

Data Index: 1376603 (Python Code)

Max Activating Token Index: 221

Text #5

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8588. Min Act: -0.0000

Data Index: 1458940 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.5598. Min Act: -0.0000

Data Index: 1458679 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1428777 (Python Code)

Max Activating Token Index: 411

Text #8

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9025. Min Act: -0.0000

Data Index: 1429906 (Python Code)

Max Activating Token Index: 156

Text #9

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.5999. Min Act: -0.0000

Data Index: 1360490 (Python Code)

Max Activating Token Index: 259

Text #10

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.4882. Min Act: -0.0000

Data Index: 1638774 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.3167. Min Act: -0.0000

Data Index: 1370359 (Python Code)

Max Activating Token Index: 209

Text #12

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1647464 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1650286 (Python Code)

Max Activating Token Index: 101

Text #14

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1567306 (Python Code)

Max Activating Token Index: 816

Text #15

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1545508 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.3220. Min Act: -0.0000

Data Index: 1643425 (Python Code)

Max Activating Token Index: 436

Text #17

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.3902. Min Act: -0.0000

Data Index: 1434437 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1559673 (Python Code)

Max Activating Token Index: 737

Text #19

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.2353. Min Act: -0.0000

Data Index: 1586619 (Python Code)

Max Activating Token Index: 224