Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2472 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1548. Min Range: -1.1548

Max Act: 1.1548. Min Act: -0.0000

Data Index: 1345779 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.8335. Min Act: -0.0000

Data Index: 468998 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1027929 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1174953 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.7522. Min Act: -0.0000

Data Index: 884766 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.8775. Min Act: -0.0000

Data Index: 194063 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.7771. Min Act: -0.0000

Data Index: 740413 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.7606. Min Act: -0.0000

Data Index: 12304 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.7150. Min Act: -0.0000

Data Index: 818651 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.7277. Min Act: -0.0000

Data Index: 125401 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1427842 (Python Code)

Max Activating Token Index: 507

Text #11

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.6619. Min Act: -0.0000

Data Index: 18837 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.6605. Min Act: -0.0000

Data Index: 542125 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.6758. Min Act: -0.0000

Data Index: 169880 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1055747 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.6374. Min Act: -0.0000

Data Index: 189868 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.6618. Min Act: -0.0000

Data Index: 913447 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.6611. Min Act: -0.0000

Data Index: 128236 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.6395. Min Act: -0.0000

Data Index: 839868 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.1548. Min Range: -1.1548

Max Act: 0.6188. Min Act: -0.0000

Data Index: 613880 (C4 (Web Text))

Max Activating Token Index: 555