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

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

Neuron 3984 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: -0.0002

Data Index: 342670 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0634. Min Act: -0.0002

Data Index: 690168 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1006994 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0556. Min Act: -0.0002

Data Index: 186454 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0526. Min Act: -0.0002

Data Index: 204357 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0538. Min Act: -0.0002

Data Index: 922175 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0501. Min Act: -0.0002

Data Index: 938220 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1213658 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0479. Min Act: -0.0002

Data Index: 600279 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0461. Min Act: -0.0002

Data Index: 665125 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0465. Min Act: -0.0002

Data Index: 163995 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0451. Min Act: -0.0002

Data Index: 773266 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0446. Min Act: -0.0002

Data Index: 584237 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0448. Min Act: -0.0002

Data Index: 577699 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0444. Min Act: -0.0003

Data Index: 485975 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1034784 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1149832 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0425. Min Act: -0.0002

Data Index: 47690 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0417. Min Act: -0.0003

Data Index: 493184 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0406. Min Act: -0.0002

Data Index: 58984 (C4 (Web Text))

Max Activating Token Index: 574