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

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

Neuron 1964 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.1010. Min Act: -0.0005

Data Index: 244274 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0880. Min Act: -0.0005

Data Index: 1221591 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0816. Min Act: -0.0005

Data Index: 644853 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0796. Min Act: -0.0005

Data Index: 905987 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0783. Min Act: -0.0005

Data Index: 41899 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0796. Min Act: -0.0005

Data Index: 989176 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0604. Min Act: -0.0005

Data Index: 710112 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0689. Min Act: -0.0005

Data Index: 1191239 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0686. Min Act: -0.0005

Data Index: 752313 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0641. Min Act: -0.0005

Data Index: 787981 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0648. Min Act: -0.0005

Data Index: 435986 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0634. Min Act: -0.0005

Data Index: 24085 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0644. Min Act: -0.0005

Data Index: 756458 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0619. Min Act: -0.0005

Data Index: 1295546 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0582. Min Act: -0.0005

Data Index: 1300660 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0615. Min Act: -0.0005

Data Index: 1192757 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0586. Min Act: -0.0005

Data Index: 1167780 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0626. Min Act: -0.0005

Data Index: 603394 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0608. Min Act: -0.0005

Data Index: 816937 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0617. Min Act: -0.0005

Data Index: 424987 (C4 (Web Text))

Max Activating Token Index: 311