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

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

Neuron 1646 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0592. Min Act: -0.0006

Data Index: 748736 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0564. Min Act: -0.0006

Data Index: 1062303 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0526. Min Act: -0.0006

Data Index: 580732 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0006

Data Index: 927117 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0530. Min Act: -0.0006

Data Index: 141007 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0503. Min Act: -0.0006

Data Index: 1303572 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0546. Min Act: -0.0006

Data Index: 994991 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0498. Min Act: -0.0006

Data Index: 81528 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0472. Min Act: -0.0006

Data Index: 39443 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0440. Min Act: -0.0006

Data Index: 637988 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0454. Min Act: -0.0006

Data Index: 675081 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0459. Min Act: -0.0006

Data Index: 655275 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0396. Min Act: -0.0006

Data Index: 1287659 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0424. Min Act: -0.0006

Data Index: 597157 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0433. Min Act: -0.0006

Data Index: 537399 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0425. Min Act: -0.0006

Data Index: 643286 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0433. Min Act: -0.0006

Data Index: 905990 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0432. Min Act: -0.0007

Data Index: 365786 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0392. Min Act: -0.0006

Data Index: 193846 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0418. Min Act: -0.0006

Data Index: 698446 (C4 (Web Text))

Max Activating Token Index: 843