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

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

Neuron 2035 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: 0.5914. Min Range: -0.5914

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1397514 (Python Code)

Max Activating Token Index: 85

Text #1

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1383800 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1478755 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1371712 (Python Code)

Max Activating Token Index: 184

Text #4

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1624276 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1583025 (Python Code)

Max Activating Token Index: 785

Text #6

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1555550 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1384608 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3082. Min Act: -0.0000

Data Index: 325703 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3185. Min Act: -0.0000

Data Index: 208194 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1401009 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1534435 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1502449 (Python Code)

Max Activating Token Index: 67

Text #13

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2835. Min Act: -0.0000

Data Index: 923024 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1594153 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1458318 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1605727 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1310124 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1514765 (Python Code)

Max Activating Token Index: 387

Text #19

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2517. Min Act: -0.0000

Data Index: 1369581 (Python Code)

Max Activating Token Index: 880