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

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

Neuron 2020 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: 1.0782. Min Range: -1.0782

Max Act: 1.0340. Min Act: -0.0001

Data Index: 809928 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.0782. Min Range: -1.0782

Max Act: 1.0608. Min Act: -0.0001

Data Index: 1061292 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.0782. Min Range: -1.0782

Max Act: 1.0359. Min Act: -0.0000

Data Index: 273008 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 1.0782. Min Range: -1.0782

Max Act: 1.0508. Min Act: -0.0001

Data Index: 103624 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9948. Min Act: -0.0001

Data Index: 539999 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9100. Min Act: -0.0001

Data Index: 236184 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9593. Min Act: -0.0001

Data Index: 22816 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 1.0782. Min Range: -1.0782

Max Act: 1.0200. Min Act: -0.0000

Data Index: 1342627 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9504. Min Act: -0.0001

Data Index: 712515 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9333. Min Act: -0.0001

Data Index: 375802 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.0782. Min Range: -1.0782

Max Act: 1.0782. Min Act: -0.0001

Data Index: 140501 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9978. Min Act: -0.0001

Data Index: 1284157 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9521. Min Act: -0.0001

Data Index: 323578 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9495. Min Act: -0.0000

Data Index: 488029 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9733. Min Act: -0.0001

Data Index: 435200 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.8263. Min Act: -0.0001

Data Index: 766643 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.8527. Min Act: -0.0001

Data Index: 774867 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9090. Min Act: -0.0001

Data Index: 340166 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.9269. Min Act: -0.0000

Data Index: 982258 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 1.0782. Min Range: -1.0782

Max Act: 0.8865. Min Act: -0.0001

Data Index: 1349368 (C4 (Web Text))

Max Activating Token Index: 555