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

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

Neuron 1622 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0001

Data Index: 236589 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1093105 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0778. Min Act: -0.0001

Data Index: 392795 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1259499 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0769. Min Act: -0.0000

Data Index: 67444 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1343353 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1128685 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1271251 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1280563 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0712. Min Act: -0.0000

Data Index: 571416 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1106156 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0715. Min Act: -0.0000

Data Index: 137463 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1236228 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0704. Min Act: -0.0001

Data Index: 705648 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0680. Min Act: -0.0000

Data Index: 608905 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0703. Min Act: -0.0001

Data Index: 204063 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0692. Min Act: -0.0001

Data Index: 836302 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0677. Min Act: -0.0001

Data Index: 702723 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1167732 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1162248 (C4 (Web Text))

Max Activating Token Index: 367