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

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

Neuron 32 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: 5.9795. Min Range: -5.9795

Max Act: 5.9795. Min Act: -0.0000

Data Index: 1566787 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.5799. Min Act: -0.0000

Data Index: 1647059 (Python Code)

Max Activating Token Index: 609

Text #2

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.5318. Min Act: -0.0000

Data Index: 1360812 (Python Code)

Max Activating Token Index: 752

Text #3

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.6221. Min Act: -0.0000

Data Index: 1531829 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.4421. Min Act: -0.0000

Data Index: 1405017 (Python Code)

Max Activating Token Index: 364

Text #5

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.4188. Min Act: -0.0000

Data Index: 1424194 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.3562. Min Act: -0.0000

Data Index: 1631099 (Python Code)

Max Activating Token Index: 953

Text #7

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.3283. Min Act: -0.0000

Data Index: 1408635 (Python Code)

Max Activating Token Index: 989

Text #8

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.0210. Min Act: -0.0000

Data Index: 1526486 (Python Code)

Max Activating Token Index: 740

Text #9

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.9044. Min Act: -0.0000

Data Index: 1516866 (Python Code)

Max Activating Token Index: 587

Text #10

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.7901. Min Act: -0.0000

Data Index: 1611277 (Python Code)

Max Activating Token Index: 266

Text #11

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.7452. Min Act: -0.0000

Data Index: 1560802 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.9106. Min Act: -0.0000

Data Index: 1407378 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.6428. Min Act: -0.0000

Data Index: 1374644 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.6098. Min Act: -0.0000

Data Index: 1410034 (Python Code)

Max Activating Token Index: 204

Text #15

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.6236. Min Act: -0.0000

Data Index: 1595794 (Python Code)

Max Activating Token Index: 267

Text #16

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.7924. Min Act: -0.0000

Data Index: 1479096 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.5122. Min Act: -0.0000

Data Index: 1482841 (Python Code)

Max Activating Token Index: 760

Text #18

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.5149. Min Act: -0.0000

Data Index: 1466664 (Python Code)

Max Activating Token Index: 397

Text #19

Max Range: 5.9795. Min Range: -5.9795

Max Act: 4.4673. Min Act: -0.0000

Data Index: 1387464 (Python Code)

Max Activating Token Index: 331