Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2897 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0773. Min Act: -0.0001

Data Index: 206000 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0782. Min Act: -0.0001

Data Index: 565170 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0744. Min Act: 0.0000

Data Index: 507034 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1136593 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0694. Min Act: 0.0001

Data Index: 721115 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0707. Min Act: -0.0001

Data Index: 586736 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1222219 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0701. Min Act: -0.0001

Data Index: 949283 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0702. Min Act: -0.0001

Data Index: 449191 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0719. Min Act: -0.0001

Data Index: 64009 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0666. Min Act: -0.0001

Data Index: 260254 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1068199 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0669. Min Act: -0.0000

Data Index: 519909 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0645. Min Act: -0.0000

Data Index: 714290 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0670. Min Act: -0.0001

Data Index: 887119 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0687. Min Act: 0.0000

Data Index: 1207619 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0656. Min Act: -0.0000

Data Index: 520909 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0646. Min Act: -0.0001

Data Index: 697921 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0628. Min Act: -0.0001

Data Index: 151343 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0646. Min Act: -0.0001

Data Index: 85099 (C4 (Web Text))

Max Activating Token Index: 356