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

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

Neuron 5006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1585612 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1563244 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1568360 (Python Code)

Max Activating Token Index: 57

Text #3

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1625957 (Python Code)

Max Activating Token Index: 918

Text #4

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1462440 (Python Code)

Max Activating Token Index: 507

Text #5

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1378088 (Python Code)

Max Activating Token Index: 736

Text #6

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1543003 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1505167 (Python Code)

Max Activating Token Index: 778

Text #8

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1393982 (Python Code)

Max Activating Token Index: 157

Text #9

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1656866 (Python Code)

Max Activating Token Index: 807

Text #10

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1479285 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1510645 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1480834 (Python Code)

Max Activating Token Index: 979

Text #13

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1422504 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1531009 (Python Code)

Max Activating Token Index: 780

Text #15

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1648742 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1436697 (Python Code)

Max Activating Token Index: 599

Text #17

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1545225 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1535115 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1495006 (Python Code)

Max Activating Token Index: 220