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

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

Neuron 1602 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.9519. Min Act: -0.0000

Data Index: 1480108 (Python Code)

Max Activating Token Index: 38

Text #1

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.4250. Min Act: -0.0000

Data Index: 1474640 (Python Code)

Max Activating Token Index: 591

Text #2

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.8995. Min Act: -0.0000

Data Index: 1587012 (Python Code)

Max Activating Token Index: 957

Text #3

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.8894. Min Act: -0.0000

Data Index: 1323749 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.6518. Min Act: -0.0000

Data Index: 98758 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.7297. Min Act: -0.0000

Data Index: 1573548 (Python Code)

Max Activating Token Index: 370

Text #6

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.7074. Min Act: -0.0000

Data Index: 1438417 (Python Code)

Max Activating Token Index: 645

Text #7

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.5649. Min Act: -0.0000

Data Index: 462325 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.3953. Min Act: -0.0000

Data Index: 387195 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.6090. Min Act: -0.0000

Data Index: 607603 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.5080. Min Act: -0.0000

Data Index: 1015411 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.4452. Min Act: -0.0000

Data Index: 732280 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.4110. Min Act: -0.0000

Data Index: 478817 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.3983. Min Act: -0.0000

Data Index: 384888 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.3941. Min Act: -0.0000

Data Index: 1226331 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.5593. Min Act: -0.0000

Data Index: 1107155 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.3575. Min Act: -0.0000

Data Index: 1530285 (Python Code)

Max Activating Token Index: 530

Text #17

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.5083. Min Act: -0.0000

Data Index: 1255280 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.2009. Min Act: -0.0000

Data Index: 1531137 (Python Code)

Max Activating Token Index: 766

Text #19

Max Range: 3.9519. Min Range: -3.9519

Max Act: 2.4327. Min Act: -0.0000

Data Index: 676081 (C4 (Web Text))

Max Activating Token Index: 227