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

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

Neuron 5 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2821. Min Range: -1.2821

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1318977 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.2821. Min Range: -1.2821

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1179266 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.2821. Min Range: -1.2821

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1407191 (Python Code)

Max Activating Token Index: 260

Text #3

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.9754. Min Act: -0.0000

Data Index: 502128 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 1.2821. Min Range: -1.2821

Max Act: 1.0381. Min Act: -0.0000

Data Index: 59887 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1587960 (Python Code)

Max Activating Token Index: 608

Text #6

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1496547 (Python Code)

Max Activating Token Index: 832

Text #7

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1502663 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 1.2821. Min Range: -1.2821

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1159835 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.8710. Min Act: -0.0000

Data Index: 154742 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1472562 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.9255. Min Act: -0.0000

Data Index: 594687 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1499563 (Python Code)

Max Activating Token Index: 920

Text #13

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.8471. Min Act: -0.0000

Data Index: 300185 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1622727 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1480853 (Python Code)

Max Activating Token Index: 567

Text #16

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1309330 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.8468. Min Act: -0.0000

Data Index: 135142 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.8832. Min Act: -0.0000

Data Index: 99075 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.2821. Min Range: -1.2821

Max Act: 0.8868. Min Act: -0.0000

Data Index: 267897 (C4 (Web Text))

Max Activating Token Index: 86