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

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

Neuron 1032 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: 1.7057. Min Range: -1.7057

Max Act: 1.7057. Min Act: -0.0001

Data Index: 1552036 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.6446. Min Act: -0.0001

Data Index: 1581986 (Python Code)

Max Activating Token Index: 390

Text #2

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.5814. Min Act: -0.0001

Data Index: 1521052 (Python Code)

Max Activating Token Index: 909

Text #3

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.3520. Min Act: -0.0001

Data Index: 1431790 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.2824. Min Act: -0.0001

Data Index: 1434240 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.3483. Min Act: -0.0001

Data Index: 1528467 (Python Code)

Max Activating Token Index: 233

Text #6

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.2844. Min Act: -0.0001

Data Index: 1523351 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1473031 (Python Code)

Max Activating Token Index: 609

Text #8

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.2374. Min Act: -0.0001

Data Index: 1473826 (Python Code)

Max Activating Token Index: 153

Text #9

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.2072. Min Act: -0.0001

Data Index: 1639805 (Python Code)

Max Activating Token Index: 735

Text #10

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.1252. Min Act: -0.0001

Data Index: 1382865 (Python Code)

Max Activating Token Index: 686

Text #11

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.0789. Min Act: -0.0001

Data Index: 1432897 (Python Code)

Max Activating Token Index: 587

Text #12

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.2717. Min Act: 0.0000

Data Index: 1471401 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.1756. Min Act: -0.0001

Data Index: 1650783 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.1523. Min Act: -0.0001

Data Index: 1565746 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.2408. Min Act: -0.0001

Data Index: 1565981 (Python Code)

Max Activating Token Index: 753

Text #16

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1546390 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.1443. Min Act: -0.0001

Data Index: 1406668 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 1.7057. Min Range: -1.7057

Max Act: 0.9818. Min Act: -0.0001

Data Index: 1626630 (Python Code)

Max Activating Token Index: 316

Text #19

Max Range: 1.7057. Min Range: -1.7057

Max Act: 1.1068. Min Act: -0.0001

Data Index: 1570581 (Python Code)

Max Activating Token Index: 983