Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 613 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0916. Min Act: -0.0002

Data Index: 227715 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1297623 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0899. Min Act: -0.0002

Data Index: 716035 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0869. Min Act: -0.0002

Data Index: 792973 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0896. Min Act: -0.0002

Data Index: 610766 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1147294 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0798. Min Act: -0.0001

Data Index: 420236 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0819. Min Act: -0.0001

Data Index: 887822 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0846. Min Act: -0.0002

Data Index: 268518 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0763. Min Act: -0.0002

Data Index: 266741 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1116784 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0734. Min Act: -0.0002

Data Index: 626467 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0774. Min Act: -0.0002

Data Index: 412575 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1237592 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1079659 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0786. Min Act: -0.0002

Data Index: 581236 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0795. Min Act: -0.0002

Data Index: 742362 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1103166 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0725. Min Act: -0.0002

Data Index: 271756 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0757. Min Act: -0.0002

Data Index: 973700 (C4 (Web Text))

Max Activating Token Index: 614