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

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

Neuron 3650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.7601. Min Act: -0.0000

Data Index: 1321985 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.7123. Min Act: -0.0000

Data Index: 224788 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.4020. Min Act: -0.0000

Data Index: 880076 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1113802 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.4444. Min Act: -0.0000

Data Index: 722621 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.3175. Min Act: -0.0000

Data Index: 486413 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.2504. Min Act: -0.0000

Data Index: 237093 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.3032. Min Act: -0.0000

Data Index: 730460 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.3440. Min Act: -0.0000

Data Index: 616466 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.3387. Min Act: -0.0000

Data Index: 783036 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.2145. Min Act: -0.0000

Data Index: 46297 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.2430. Min Act: -0.0000

Data Index: 1328141 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.1803. Min Act: -0.0000

Data Index: 881954 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1217589 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1273932 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.1370. Min Act: -0.0000

Data Index: 547449 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1403180 (Python Code)

Max Activating Token Index: 269

Text #17

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1116623 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.1770. Min Act: -0.0000

Data Index: 269194 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 1.7601. Min Range: -1.7601

Max Act: 1.1650. Min Act: -0.0000

Data Index: 229594 (C4 (Web Text))

Max Activating Token Index: 492