Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 890 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6798. Min Act: -0.0001

Data Index: 577362 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6455. Min Act: -0.0001

Data Index: 173398 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6797. Min Act: -0.0001

Data Index: 388923 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5697. Min Act: -0.0001

Data Index: 855184 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5417. Min Act: -0.0001

Data Index: 197945 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5896. Min Act: -0.0001

Data Index: 599599 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5802. Min Act: -0.0001

Data Index: 343911 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5644. Min Act: -0.0001

Data Index: 353570 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5999. Min Act: -0.0001

Data Index: 181071 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5521. Min Act: -0.0001

Data Index: 975982 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5831. Min Act: -0.0001

Data Index: 1228953 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5659. Min Act: -0.0001

Data Index: 105032 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5628. Min Act: -0.0001

Data Index: 493624 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5419. Min Act: -0.0001

Data Index: 285949 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5376. Min Act: -0.0001

Data Index: 618868 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5594. Min Act: -0.0001

Data Index: 998597 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4339. Min Act: -0.0001

Data Index: 564337 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5558. Min Act: -0.0001

Data Index: 289061 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5326. Min Act: -0.0001

Data Index: 545808 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5605. Min Act: -0.0001

Data Index: 7091 (C4 (Web Text))

Max Activating Token Index: 987