Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3632 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3608. Min Act: -0.0001

Data Index: 138103 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3409. Min Act: -0.0001

Data Index: 650352 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3473. Min Act: -0.0001

Data Index: 751660 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3611. Min Act: -0.0001

Data Index: 890032 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3375. Min Act: -0.0001

Data Index: 235267 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3441. Min Act: -0.0001

Data Index: 426522 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3154. Min Act: -0.0001

Data Index: 862503 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3195. Min Act: -0.0001

Data Index: 572594 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2917. Min Act: -0.0001

Data Index: 640742 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2978. Min Act: -0.0001

Data Index: 229844 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2968. Min Act: -0.0001

Data Index: 1216537 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2954. Min Act: -0.0001

Data Index: 370606 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2787. Min Act: -0.0001

Data Index: 45257 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2871. Min Act: -0.0001

Data Index: 86977 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2786. Min Act: -0.0001

Data Index: 581826 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2761. Min Act: -0.0001

Data Index: 1230596 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2760. Min Act: -0.0001

Data Index: 700573 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2721. Min Act: -0.0001

Data Index: 845392 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2632. Min Act: -0.0001

Data Index: 993322 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2783. Min Act: -0.0001

Data Index: 360725 (C4 (Web Text))

Max Activating Token Index: 278