Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3672 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.9638. Min Act: -0.0002

Data Index: 1238920 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8490. Min Act: -0.0001

Data Index: 1248163 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8620. Min Act: -0.0001

Data Index: 895492 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7854. Min Act: -0.0001

Data Index: 932459 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7887. Min Act: -0.0001

Data Index: 1390319 (Python Code)

Max Activating Token Index: 321

Text #5

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6965. Min Act: -0.0001

Data Index: 425661 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7334. Min Act: -0.0001

Data Index: 1333756 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7146. Min Act: -0.0001

Data Index: 725786 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7345. Min Act: -0.0002

Data Index: 845046 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7546. Min Act: -0.0001

Data Index: 576195 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6818. Min Act: -0.0001

Data Index: 334121 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7046. Min Act: -0.0001

Data Index: 1198532 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6829. Min Act: -0.0001

Data Index: 1280361 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7200. Min Act: -0.0001

Data Index: 1120768 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7526. Min Act: -0.0002

Data Index: 662579 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7316. Min Act: -0.0002

Data Index: 1172071 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1059766 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7249. Min Act: -0.0001

Data Index: 1647650 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6757. Min Act: -0.0002

Data Index: 192673 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6997. Min Act: -0.0002

Data Index: 640899 (C4 (Web Text))

Max Activating Token Index: 400