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

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

Neuron 3877 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0499. Min Range: -1.0499

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1551197 (Python Code)

Max Activating Token Index: 157

Text #1

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1444500 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1492732 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1493178 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1593131 (Python Code)

Max Activating Token Index: 265

Text #5

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1559597 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1533438 (Python Code)

Max Activating Token Index: 332

Text #7

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1426363 (Python Code)

Max Activating Token Index: 478

Text #8

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1397144 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1593817 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1502118 (Python Code)

Max Activating Token Index: 122

Text #11

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1474667 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1584120 (Python Code)

Max Activating Token Index: 549

Text #13

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1645613 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1454852 (Python Code)

Max Activating Token Index: 595

Text #15

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1433015 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1609132 (Python Code)

Max Activating Token Index: 490

Text #17

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1395938 (Python Code)

Max Activating Token Index: 759

Text #18

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1418298 (Python Code)

Max Activating Token Index: 202

Text #19

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1609713 (Python Code)

Max Activating Token Index: 523