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

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

Neuron 3041 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: 0.0771. Min Range: -0.0771

Max Act: 0.0771. Min Act: -0.0001

Data Index: 885574 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0650. Min Act: -0.0001

Data Index: 445297 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0590. Min Act: -0.0001

Data Index: 515807 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0585. Min Act: -0.0001

Data Index: 113160 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0648. Min Act: -0.0001

Data Index: 972435 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1329667 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0730. Min Act: -0.0001

Data Index: 452550 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1232667 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0606. Min Act: -0.0001

Data Index: 429020 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0636. Min Act: -0.0001

Data Index: 896697 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0648. Min Act: -0.0001

Data Index: 789498 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1264767 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0572. Min Act: -0.0001

Data Index: 469750 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1084540 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1101421 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0552. Min Act: -0.0001

Data Index: 487278 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0535. Min Act: -0.0001

Data Index: 492423 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1259927 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0583. Min Act: -0.0001

Data Index: 569181 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0523. Min Act: -0.0001

Data Index: 890159 (C4 (Web Text))

Max Activating Token Index: 888