Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1393418 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8624. Min Act: -0.0001

Data Index: 1369860 (Python Code)

Max Activating Token Index: 241

Text #2

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1448985 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7095. Min Act: -0.0001

Data Index: 1564444 (Python Code)

Max Activating Token Index: 873

Text #4

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1376035 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7794. Min Act: -0.0001

Data Index: 1471369 (Python Code)

Max Activating Token Index: 966

Text #6

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7549. Min Act: -0.0001

Data Index: 1423585 (Python Code)

Max Activating Token Index: 332

Text #7

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.6958. Min Act: -0.0001

Data Index: 1473571 (Python Code)

Max Activating Token Index: 455

Text #8

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1456723 (Python Code)

Max Activating Token Index: 114

Text #9

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1605529 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.6995. Min Act: -0.0001

Data Index: 1637130 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.6359. Min Act: -0.0001

Data Index: 1551320 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7092. Min Act: -0.0001

Data Index: 1591346 (Python Code)

Max Activating Token Index: 472

Text #13

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1587772 (Python Code)

Max Activating Token Index: 972

Text #14

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1497458 (Python Code)

Max Activating Token Index: 762

Text #15

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7516. Min Act: -0.0001

Data Index: 1586395 (Python Code)

Max Activating Token Index: 472

Text #16

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.6792. Min Act: -0.0001

Data Index: 1634032 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7483. Min Act: -0.0001

Data Index: 1360637 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.6973. Min Act: -0.0001

Data Index: 1446170 (Python Code)

Max Activating Token Index: 776

Text #19

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.6875. Min Act: -0.0001

Data Index: 1540153 (Python Code)

Max Activating Token Index: 539