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

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

Neuron 2470 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0001

Data Index: 427158 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1209022 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1007673 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1161216 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0759. Min Act: -0.0001

Data Index: 718648 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1592892 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0692. Min Act: -0.0001

Data Index: 920585 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0686. Min Act: -0.0001

Data Index: 967381 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1220635 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0645. Min Act: -0.0001

Data Index: 823144 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1085896 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0687. Min Act: -0.0001

Data Index: 297034 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0650. Min Act: -0.0002

Data Index: 366731 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0689. Min Act: -0.0001

Data Index: 169052 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0638. Min Act: -0.0001

Data Index: 402816 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1004382 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0621. Min Act: -0.0001

Data Index: 999125 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0602. Min Act: -0.0001

Data Index: 996014 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1016637 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1048277 (C4 (Web Text))

Max Activating Token Index: 409