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

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

Neuron 4643 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.7707. Min Act: -0.0000

Data Index: 811606 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1359731 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6949. Min Act: -0.0000

Data Index: 708542 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6645. Min Act: -0.0000

Data Index: 984775 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6340. Min Act: -0.0000

Data Index: 787975 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1021585 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6105. Min Act: 0.0000

Data Index: 473935 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6311. Min Act: 0.0000

Data Index: 125903 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1219890 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5854. Min Act: 0.0000

Data Index: 775376 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5686. Min Act: -0.0000

Data Index: 91005 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1100252 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1214485 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5692. Min Act: 0.0000

Data Index: 122962 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5641. Min Act: -0.0000

Data Index: 909333 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5337. Min Act: -0.0000

Data Index: 775522 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5421. Min Act: -0.0000

Data Index: 77281 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5522. Min Act: 0.0001

Data Index: 810793 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5889. Min Act: 0.0000

Data Index: 722241 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5278. Min Act: -0.0000

Data Index: 777459 (C4 (Web Text))

Max Activating Token Index: 393