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

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

Neuron 4238 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4509. Min Act: -0.0001

Data Index: 1406823 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.5475. Min Act: -0.0001

Data Index: 1508889 (Python Code)

Max Activating Token Index: 698

Text #2

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4301. Min Act: -0.0001

Data Index: 1505489 (Python Code)

Max Activating Token Index: 1020

Text #3

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4542. Min Act: -0.0001

Data Index: 1499239 (Python Code)

Max Activating Token Index: 654

Text #4

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1529713 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1608041 (Python Code)

Max Activating Token Index: 480

Text #6

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.2177. Min Act: -0.0001

Data Index: 1433493 (Python Code)

Max Activating Token Index: 678

Text #7

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.2327. Min Act: -0.0001

Data Index: 1364538 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1643898 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.2173. Min Act: -0.0001

Data Index: 1388057 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.2107. Min Act: -0.0001

Data Index: 1620727 (Python Code)

Max Activating Token Index: 552

Text #11

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.2084. Min Act: -0.0000

Data Index: 1604869 (Python Code)

Max Activating Token Index: 149

Text #12

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.3193. Min Act: -0.0001

Data Index: 1611699 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.1694. Min Act: -0.0001

Data Index: 1480007 (Python Code)

Max Activating Token Index: 155

Text #14

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.0182. Min Act: -0.0001

Data Index: 1365919 (Python Code)

Max Activating Token Index: 798

Text #15

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.2253. Min Act: -0.0001

Data Index: 1381353 (Python Code)

Max Activating Token Index: 718

Text #16

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1387518 (Python Code)

Max Activating Token Index: 737

Text #17

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.1601. Min Act: -0.0001

Data Index: 1492772 (Python Code)

Max Activating Token Index: 825

Text #18

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1593542 (Python Code)

Max Activating Token Index: 720

Text #19

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1529766 (Python Code)

Max Activating Token Index: 390