Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2734 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1291720 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.2855. Min Act: -0.0001

Data Index: 535886 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.2722. Min Act: -0.0000

Data Index: 295245 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.3339. Min Act: -0.0001

Data Index: 1036536 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.2494. Min Act: -0.0000

Data Index: 528970 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.2497. Min Act: -0.0000

Data Index: 1134971 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.2135. Min Act: -0.0001

Data Index: 279219 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1028601 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.1102. Min Act: -0.0001

Data Index: 552212 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.1014. Min Act: -0.0001

Data Index: 123097 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.0695. Min Act: -0.0000

Data Index: 377058 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9709. Min Act: -0.0001

Data Index: 845692 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9989. Min Act: -0.0001

Data Index: 132840 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9698. Min Act: -0.0001

Data Index: 1229772 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.0211. Min Act: -0.0001

Data Index: 843170 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9700. Min Act: -0.0001

Data Index: 909788 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9619. Min Act: -0.0000

Data Index: 383271 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.0436. Min Act: -0.0001

Data Index: 588978 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9485. Min Act: -0.0001

Data Index: 189568 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9892. Min Act: -0.0001

Data Index: 1145104 (C4 (Web Text))

Max Activating Token Index: 124