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

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

Neuron 5075 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8622. Min Act: -0.0002

Data Index: 1377096 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8636. Min Act: -0.0002

Data Index: 1569402 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8514. Min Act: -0.0002

Data Index: 1431768 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.9289. Min Act: -0.0002

Data Index: 1645600 (Python Code)

Max Activating Token Index: 333

Text #4

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8606. Min Act: -0.0002

Data Index: 1454963 (Python Code)

Max Activating Token Index: 189

Text #5

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8341. Min Act: -0.0002

Data Index: 1559520 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7878. Min Act: -0.0002

Data Index: 1596977 (Python Code)

Max Activating Token Index: 197

Text #7

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8293. Min Act: -0.0002

Data Index: 1378140 (Python Code)

Max Activating Token Index: 189

Text #8

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8050. Min Act: -0.0002

Data Index: 1476581 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8084. Min Act: -0.0002

Data Index: 1411963 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7955. Min Act: -0.0002

Data Index: 1454992 (Python Code)

Max Activating Token Index: 171

Text #11

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7503. Min Act: -0.0002

Data Index: 1652456 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8160. Min Act: -0.0002

Data Index: 1472484 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7760. Min Act: -0.0002

Data Index: 1527883 (Python Code)

Max Activating Token Index: 160

Text #14

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7719. Min Act: -0.0002

Data Index: 1506707 (Python Code)

Max Activating Token Index: 140

Text #15

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7469. Min Act: -0.0002

Data Index: 1585121 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8143. Min Act: -0.0002

Data Index: 1518674 (Python Code)

Max Activating Token Index: 466

Text #17

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8435. Min Act: -0.0002

Data Index: 1418554 (Python Code)

Max Activating Token Index: 174

Text #18

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7860. Min Act: -0.0002

Data Index: 1453280 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8487. Min Act: -0.0002

Data Index: 1438821 (Python Code)

Max Activating Token Index: 142