Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5493 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1766. Min Range: -3.1766

Max Act: 3.1766. Min Act: -0.0000

Data Index: 796513 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.6701. Min Act: -0.0000

Data Index: 825475 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.5743. Min Act: -0.0000

Data Index: 261026 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.6712. Min Act: -0.0000

Data Index: 1269263 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.4316. Min Act: -0.0000

Data Index: 671770 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.4291. Min Act: -0.0000

Data Index: 1222844 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.2993. Min Act: -0.0000

Data Index: 829143 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.2437. Min Act: -0.0000

Data Index: 1195979 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.1309. Min Act: -0.0000

Data Index: 272655 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 3.1766. Min Range: -3.1766

Max Act: 1.7687. Min Act: -0.0000

Data Index: 897947 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.0894. Min Act: -0.0000

Data Index: 489869 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 3.1766. Min Range: -3.1766

Max Act: 1.9362. Min Act: -0.0000

Data Index: 139628 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.0063. Min Act: -0.0000

Data Index: 502077 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 3.1766. Min Range: -3.1766

Max Act: 1.9912. Min Act: -0.0000

Data Index: 667765 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 3.1766. Min Range: -3.1766

Max Act: 1.9878. Min Act: -0.0000

Data Index: 202990 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.0949. Min Act: -0.0000

Data Index: 898820 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 3.1766. Min Range: -3.1766

Max Act: 1.9779. Min Act: -0.0000

Data Index: 334091 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 3.1766. Min Range: -3.1766

Max Act: 1.9782. Min Act: -0.0000

Data Index: 1232521 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 3.1766. Min Range: -3.1766

Max Act: 1.9632. Min Act: -0.0000

Data Index: 122554 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.0590. Min Act: -0.0000

Data Index: 725448 (C4 (Web Text))

Max Activating Token Index: 778