Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4659 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2067. Min Range: -5.2067

Max Act: 5.2067. Min Act: -0.0000

Data Index: 1577602 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.8886. Min Act: -0.0000

Data Index: 1585739 (Python Code)

Max Activating Token Index: 412

Text #2

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.4639. Min Act: -0.0000

Data Index: 1624024 (Python Code)

Max Activating Token Index: 716

Text #3

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.6180. Min Act: -0.0000

Data Index: 1582277 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.4364. Min Act: -0.0000

Data Index: 1548931 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.5823. Min Act: -0.0000

Data Index: 1542726 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.1595. Min Act: -0.0000

Data Index: 1503267 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.3504. Min Act: -0.0000

Data Index: 1610889 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.1587. Min Act: -0.0000

Data Index: 1556278 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.4813. Min Act: -0.0000

Data Index: 1376137 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.2789. Min Act: -0.0000

Data Index: 1630450 (Python Code)

Max Activating Token Index: 376

Text #11

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.0949. Min Act: -0.0000

Data Index: 1650109 (Python Code)

Max Activating Token Index: 471

Text #12

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.4178. Min Act: -0.0000

Data Index: 1586942 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.0685. Min Act: -0.0000

Data Index: 1645151 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.4207. Min Act: -0.0000

Data Index: 1611158 (Python Code)

Max Activating Token Index: 522

Text #15

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.2247. Min Act: -0.0000

Data Index: 1474375 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 5.2067. Min Range: -5.2067

Max Act: 3.9931. Min Act: -0.0000

Data Index: 1538171 (Python Code)

Max Activating Token Index: 743

Text #17

Max Range: 5.2067. Min Range: -5.2067

Max Act: 3.9971. Min Act: -0.0000

Data Index: 1609913 (Python Code)

Max Activating Token Index: 818

Text #18

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.1535. Min Act: -0.0000

Data Index: 1417916 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 5.2067. Min Range: -5.2067

Max Act: 4.1491. Min Act: -0.0000

Data Index: 1406315 (Python Code)

Max Activating Token Index: 218