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

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

Neuron 3666 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.1468. Min Act: -0.0001

Data Index: 1318227 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.1221. Min Act: -0.0000

Data Index: 880105 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0445. Min Act: -0.0001

Data Index: 157999 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0421. Min Act: -0.0001

Data Index: 655248 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8747. Min Act: -0.0001

Data Index: 1198114 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8133. Min Act: -0.0001

Data Index: 77016 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7971. Min Act: -0.0001

Data Index: 1347550 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7633. Min Act: -0.0001

Data Index: 643308 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7755. Min Act: -0.0001

Data Index: 852888 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7510. Min Act: -0.0001

Data Index: 521805 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7000. Min Act: -0.0001

Data Index: 1243750 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7292. Min Act: -0.0000

Data Index: 727884 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.6875. Min Act: -0.0001

Data Index: 1174795 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.6518. Min Act: -0.0001

Data Index: 627833 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.6830. Min Act: -0.0001

Data Index: 665890 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.6902. Min Act: -0.0001

Data Index: 550283 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7112. Min Act: -0.0001

Data Index: 937920 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.6776. Min Act: -0.0001

Data Index: 1173725 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1162697 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.6915. Min Act: -0.0001

Data Index: 758073 (C4 (Web Text))

Max Activating Token Index: 529