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

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

Neuron 5860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: -0.0001

Data Index: 687181 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: -0.0000

Data Index: 53502 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1506145 (Python Code)

Max Activating Token Index: 576

Text #3

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0846. Min Act: -0.0000

Data Index: 419688 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1633127 (Python Code)

Max Activating Token Index: 958

Text #5

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0862. Min Act: -0.0001

Data Index: 940193 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1050722 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1302026 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0719. Min Act: -0.0000

Data Index: 921306 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0749. Min Act: -0.0000

Data Index: 557508 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0705. Min Act: -0.0000

Data Index: 882289 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0724. Min Act: -0.0000

Data Index: 976500 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0699. Min Act: -0.0000

Data Index: 1557158 (Python Code)

Max Activating Token Index: 978

Text #13

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0699. Min Act: -0.0001

Data Index: 60739 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0754. Min Act: -0.0000

Data Index: 984505 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0694. Min Act: -0.0000

Data Index: 237920 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0769. Min Act: -0.0001

Data Index: 374742 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0700. Min Act: -0.0001

Data Index: 733566 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1145601 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0633. Min Act: -0.0001

Data Index: 118270 (C4 (Web Text))

Max Activating Token Index: 894