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

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

Neuron 4080 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1545141 (Python Code)

Max Activating Token Index: 405

Text #1

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1565742 (Python Code)

Max Activating Token Index: 247

Text #2

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.4784. Min Act: -0.0000

Data Index: 1552820 (Python Code)

Max Activating Token Index: 199

Text #3

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.4172. Min Act: -0.0001

Data Index: 1374506 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1552193 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1604654 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1542722 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1653479 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1403512 (Python Code)

Max Activating Token Index: 898

Text #9

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.2094. Min Act: -0.0000

Data Index: 1465272 (Python Code)

Max Activating Token Index: 873

Text #10

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1499194 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1546. Min Act: -0.0000

Data Index: 1430422 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1376783 (Python Code)

Max Activating Token Index: 247

Text #13

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1627134 (Python Code)

Max Activating Token Index: 113

Text #14

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1487399 (Python Code)

Max Activating Token Index: 83

Text #15

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1083. Min Act: -0.0000

Data Index: 1378469 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1588559 (Python Code)

Max Activating Token Index: 218

Text #17

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1589659 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0265. Min Act: -0.0000

Data Index: 1506506 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1623178 (Python Code)

Max Activating Token Index: 72