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

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

Neuron 4789 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: 1.5041. Min Range: -1.5041

Max Act: 1.5041. Min Act: -0.0000

Data Index: 1575093 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.4792. Min Act: -0.0000

Data Index: 1497235 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1421678 (Python Code)

Max Activating Token Index: 401

Text #3

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.3645. Min Act: -0.0000

Data Index: 1066417 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1398352 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.3499. Min Act: -0.0000

Data Index: 294662 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1556023 (Python Code)

Max Activating Token Index: 174

Text #7

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.3025. Min Act: -0.0000

Data Index: 1467325 (Python Code)

Max Activating Token Index: 79

Text #8

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.2486. Min Act: -0.0000

Data Index: 1634130 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1556101 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1579695 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1649394 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1365285 (Python Code)

Max Activating Token Index: 210

Text #13

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.2197. Min Act: -0.0000

Data Index: 1575851 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1057102 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1594656 (Python Code)

Max Activating Token Index: 369

Text #16

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1572490 (Python Code)

Max Activating Token Index: 1010

Text #17

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.0718. Min Act: -0.0000

Data Index: 1484100 (Python Code)

Max Activating Token Index: 707

Text #18

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.1606. Min Act: -0.0000

Data Index: 1559785 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 1.5041. Min Range: -1.5041

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1507958 (Python Code)

Max Activating Token Index: 64