Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5089 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0918. Min Act: -0.0001

Data Index: 514506 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0854. Min Act: -0.0001

Data Index: 943633 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0807. Min Act: -0.0001

Data Index: 128483 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0786. Min Act: -0.0001

Data Index: 712551 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0751. Min Act: -0.0001

Data Index: 661236 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0782. Min Act: -0.0001

Data Index: 385366 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1257252 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1004980 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1120161 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0696. Min Act: -0.0001

Data Index: 218314 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1313730 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0602. Min Act: -0.0001

Data Index: 18739 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0555. Min Act: -0.0001

Data Index: 936986 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1233509 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1257334 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0498. Min Act: -0.0001

Data Index: 417267 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1029554 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0594. Min Act: -0.0001

Data Index: 484552 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1382435 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0505. Min Act: -0.0001

Data Index: 27414 (C4 (Web Text))

Max Activating Token Index: 871