Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1415 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0617. Min Act: -0.0005

Data Index: 589844 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0576. Min Act: -0.0006

Data Index: 308765 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0575. Min Act: -0.0006

Data Index: 384813 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0569. Min Act: -0.0006

Data Index: 303748 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0544. Min Act: -0.0005

Data Index: 858036 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0517. Min Act: -0.0006

Data Index: 618281 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0570. Min Act: -0.0005

Data Index: 450973 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0520. Min Act: -0.0006

Data Index: 54596 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0530. Min Act: -0.0005

Data Index: 673601 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0526. Min Act: -0.0005

Data Index: 357372 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0528. Min Act: -0.0005

Data Index: 1584959 (Python Code)

Max Activating Token Index: 234

Text #11

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0515. Min Act: -0.0006

Data Index: 843847 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0521. Min Act: -0.0005

Data Index: 793556 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0494. Min Act: -0.0006

Data Index: 1148440 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0501. Min Act: -0.0006

Data Index: 1260831 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0490. Min Act: -0.0006

Data Index: 920570 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0490. Min Act: -0.0005

Data Index: 728093 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0489. Min Act: -0.0006

Data Index: 407035 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1057105 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1258158 (C4 (Web Text))

Max Activating Token Index: 18