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

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

Neuron 3423 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.4361. Min Act: -0.0000

Data Index: 1614779 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.1388. Min Act: -0.0000

Data Index: 1470570 (Python Code)

Max Activating Token Index: 917

Text #2

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1547787 (Python Code)

Max Activating Token Index: 168

Text #3

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1587949 (Python Code)

Max Activating Token Index: 466

Text #4

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1581043 (Python Code)

Max Activating Token Index: 556

Text #5

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1503811 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1549642 (Python Code)

Max Activating Token Index: 530

Text #7

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1392604 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1415379 (Python Code)

Max Activating Token Index: 79

Text #9

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1454603 (Python Code)

Max Activating Token Index: 140

Text #10

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1530049 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1531676 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1567923 (Python Code)

Max Activating Token Index: 689

Text #13

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1650653 (Python Code)

Max Activating Token Index: 762

Text #14

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1619067 (Python Code)

Max Activating Token Index: 731

Text #15

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1530125 (Python Code)

Max Activating Token Index: 896

Text #16

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1654204 (Python Code)

Max Activating Token Index: 397

Text #17

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1593220 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1364830 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 1.4361. Min Range: -1.4361

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1452937 (Python Code)

Max Activating Token Index: 623