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

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

Neuron 2111 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: 2.6100. Min Range: -2.6100

Max Act: 2.6100. Min Act: -0.0000

Data Index: 1601738 (Python Code)

Max Activating Token Index: 718

Text #1

Max Range: 2.6100. Min Range: -2.6100

Max Act: 2.5827. Min Act: -0.0000

Data Index: 1446049 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 2.6100. Min Range: -2.6100

Max Act: 2.4548. Min Act: 0.0000

Data Index: 441746 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 2.6100. Min Range: -2.6100

Max Act: 2.3119. Min Act: -0.0000

Data Index: 1521717 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 2.6100. Min Range: -2.6100

Max Act: 2.1106. Min Act: -0.0000

Data Index: 1585336 (Python Code)

Max Activating Token Index: 621

Text #5

Max Range: 2.6100. Min Range: -2.6100

Max Act: 2.1702. Min Act: -0.0000

Data Index: 1572878 (Python Code)

Max Activating Token Index: 961

Text #6

Max Range: 2.6100. Min Range: -2.6100

Max Act: 2.0757. Min Act: -0.0000

Data Index: 136385 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.9740. Min Act: -0.0000

Data Index: 1581408 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.8466. Min Act: -0.0000

Data Index: 1467591 (Python Code)

Max Activating Token Index: 712

Text #9

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.8112. Min Act: -0.0000

Data Index: 250492 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.9432. Min Act: -0.0000

Data Index: 1500377 (Python Code)

Max Activating Token Index: 985

Text #11

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.9018. Min Act: -0.0000

Data Index: 1544654 (Python Code)

Max Activating Token Index: 615

Text #12

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.8564. Min Act: -0.0000

Data Index: 1629460 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1475499 (Python Code)

Max Activating Token Index: 387

Text #14

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.8547. Min Act: -0.0000

Data Index: 1602040 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.8144. Min Act: -0.0000

Data Index: 1419640 (Python Code)

Max Activating Token Index: 658

Text #16

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.8221. Min Act: -0.0000

Data Index: 1528934 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.8010. Min Act: 0.0000

Data Index: 1632851 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.7677. Min Act: -0.0000

Data Index: 1392960 (Python Code)

Max Activating Token Index: 731

Text #19

Max Range: 2.6100. Min Range: -2.6100

Max Act: 1.9572. Min Act: -0.0000

Data Index: 1653698 (Python Code)

Max Activating Token Index: 204