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

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

Neuron 333 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: 2.4434. Min Range: -2.4434

Max Act: 2.3868. Min Act: -0.0000

Data Index: 1583264 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.4434. Min Act: -0.0000

Data Index: 1642434 (Python Code)

Max Activating Token Index: 380

Text #2

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.3082. Min Act: -0.0000

Data Index: 1596924 (Python Code)

Max Activating Token Index: 249

Text #3

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.2966. Min Act: -0.0000

Data Index: 1584341 (Python Code)

Max Activating Token Index: 507

Text #4

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.1521. Min Act: -0.0000

Data Index: 1424807 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.1087. Min Act: -0.0000

Data Index: 1566507 (Python Code)

Max Activating Token Index: 919

Text #6

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.0019. Min Act: 0.0000

Data Index: 1415135 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 2.4434. Min Range: -2.4434

Max Act: 1.9848. Min Act: -0.0000

Data Index: 1627872 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.2084. Min Act: -0.0000

Data Index: 1499836 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 2.4434. Min Range: -2.4434

Max Act: 1.8311. Min Act: -0.0000

Data Index: 1411131 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.1329. Min Act: -0.0000

Data Index: 1485316 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.0274. Min Act: -0.0000

Data Index: 1384110 (Python Code)

Max Activating Token Index: 823

Text #12

Max Range: 2.4434. Min Range: -2.4434

Max Act: 2.0158. Min Act: -0.0000

Data Index: 1650871 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 2.4434. Min Range: -2.4434

Max Act: 1.8434. Min Act: -0.0000

Data Index: 1568238 (Python Code)

Max Activating Token Index: 265

Text #14

Max Range: 2.4434. Min Range: -2.4434

Max Act: 1.8422. Min Act: -0.0000

Data Index: 1460511 (Python Code)

Max Activating Token Index: 620

Text #15

Max Range: 2.4434. Min Range: -2.4434

Max Act: 1.7037. Min Act: -0.0000

Data Index: 1432070 (Python Code)

Max Activating Token Index: 411

Text #16

Max Range: 2.4434. Min Range: -2.4434

Max Act: 1.8121. Min Act: -0.0000

Data Index: 1424769 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 2.4434. Min Range: -2.4434

Max Act: 1.7069. Min Act: -0.0000

Data Index: 1621484 (Python Code)

Max Activating Token Index: 991

Text #18

Max Range: 2.4434. Min Range: -2.4434

Max Act: 1.5936. Min Act: 0.0000

Data Index: 1588293 (Python Code)

Max Activating Token Index: 300

Text #19

Max Range: 2.4434. Min Range: -2.4434

Max Act: 1.7282. Min Act: -0.0000

Data Index: 1476781 (Python Code)

Max Activating Token Index: 642