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

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

Neuron 4581 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.4085. Min Act: -0.0000

Data Index: 1627619 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.7910. Min Act: -0.0000

Data Index: 1589699 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.6333. Min Act: -0.0000

Data Index: 1488153 (Python Code)

Max Activating Token Index: 224

Text #3

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.5184. Min Act: -0.0000

Data Index: 1626124 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.3984. Min Act: -0.0000

Data Index: 1642306 (Python Code)

Max Activating Token Index: 166

Text #5

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.2144. Min Act: -0.0000

Data Index: 1407734 (Python Code)

Max Activating Token Index: 890

Text #6

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.0525. Min Act: -0.0000

Data Index: 1422636 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.1207. Min Act: -0.0000

Data Index: 1655372 (Python Code)

Max Activating Token Index: 113

Text #8

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.1239. Min Act: -0.0000

Data Index: 1489116 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 2.7910. Min Range: -2.7910

Max Act: 1.9453. Min Act: -0.0000

Data Index: 1425028 (Python Code)

Max Activating Token Index: 842

Text #10

Max Range: 2.7910. Min Range: -2.7910

Max Act: 1.9513. Min Act: -0.0000

Data Index: 1447390 (Python Code)

Max Activating Token Index: 888

Text #11

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.0741. Min Act: -0.0000

Data Index: 1401794 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 2.7910. Min Range: -2.7910

Max Act: 2.0902. Min Act: -0.0000

Data Index: 1411739 (Python Code)

Max Activating Token Index: 714

Text #13

Max Range: 2.7910. Min Range: -2.7910

Max Act: 1.9552. Min Act: -0.0000

Data Index: 1504259 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 2.7910. Min Range: -2.7910

Max Act: 1.9606. Min Act: -0.0000

Data Index: 1606261 (Python Code)

Max Activating Token Index: 181

Text #15

Max Range: 2.7910. Min Range: -2.7910

Max Act: 1.7300. Min Act: -0.0000

Data Index: 1649574 (Python Code)

Max Activating Token Index: 912

Text #16

Max Range: 2.7910. Min Range: -2.7910

Max Act: 1.8119. Min Act: -0.0000

Data Index: 1507359 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 2.7910. Min Range: -2.7910

Max Act: 1.9876. Min Act: -0.0000

Data Index: 1547870 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 2.7910. Min Range: -2.7910

Max Act: 1.8895. Min Act: -0.0000

Data Index: 1532950 (Python Code)

Max Activating Token Index: 220

Text #19

Max Range: 2.7910. Min Range: -2.7910

Max Act: 1.8781. Min Act: -0.0000

Data Index: 1451817 (Python Code)

Max Activating Token Index: 975