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

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

Neuron 627 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.7650. Min Act: -0.0000

Data Index: 1205538 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.5357. Min Act: -0.0000

Data Index: 1391539 (Python Code)

Max Activating Token Index: 986

Text #2

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.1758. Min Act: -0.0000

Data Index: 1395488 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.2013. Min Act: -0.0000

Data Index: 1493465 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.1553. Min Act: -0.0000

Data Index: 610642 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.0141. Min Act: -0.0000

Data Index: 1414519 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.2925. Min Act: -0.0000

Data Index: 847591 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 3.7650. Min Range: -3.7650

Max Act: 2.9922. Min Act: -0.0000

Data Index: 1511617 (Python Code)

Max Activating Token Index: 837

Text #8

Max Range: 3.7650. Min Range: -3.7650

Max Act: 2.9619. Min Act: -0.0000

Data Index: 724415 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.2249. Min Act: -0.0000

Data Index: 1463594 (Python Code)

Max Activating Token Index: 967

Text #10

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.0388. Min Act: -0.0000

Data Index: 1637961 (Python Code)

Max Activating Token Index: 526

Text #11

Max Range: 3.7650. Min Range: -3.7650

Max Act: 2.9975. Min Act: -0.0000

Data Index: 510254 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 3.7650. Min Range: -3.7650

Max Act: 2.7012. Min Act: -0.0000

Data Index: 1515511 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 3.7650. Min Range: -3.7650

Max Act: 2.8295. Min Act: -0.0000

Data Index: 718308 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.2778. Min Act: -0.0000

Data Index: 834293 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 3.7650. Min Range: -3.7650

Max Act: 2.9767. Min Act: -0.0000

Data Index: 1602720 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 3.7650. Min Range: -3.7650

Max Act: 3.1138. Min Act: -0.0000

Data Index: 726214 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 3.7650. Min Range: -3.7650

Max Act: 2.8200. Min Act: -0.0000

Data Index: 1953 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 3.7650. Min Range: -3.7650

Max Act: 2.9390. Min Act: -0.0000

Data Index: 1586052 (Python Code)

Max Activating Token Index: 48

Text #19

Max Range: 3.7650. Min Range: -3.7650

Max Act: 2.8072. Min Act: -0.0000

Data Index: 369725 (C4 (Web Text))

Max Activating Token Index: 917