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

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

Neuron 2595 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.1848. Min Act: -0.0001

Data Index: 579974 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.0711. Min Act: -0.0001

Data Index: 751145 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.0404. Min Act: -0.0001

Data Index: 1167284 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9966. Min Act: -0.0001

Data Index: 936933 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.0108. Min Act: -0.0001

Data Index: 418117 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9696. Min Act: -0.0001

Data Index: 1013437 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.0134. Min Act: -0.0001

Data Index: 88954 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.0084. Min Act: -0.0001

Data Index: 1243162 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9739. Min Act: -0.0001

Data Index: 451495 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9655. Min Act: -0.0001

Data Index: 1125846 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9341. Min Act: -0.0001

Data Index: 586600 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9011. Min Act: -0.0001

Data Index: 824577 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8847. Min Act: -0.0001

Data Index: 277867 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8891. Min Act: -0.0001

Data Index: 307062 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8793. Min Act: -0.0001

Data Index: 588090 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8683. Min Act: -0.0001

Data Index: 1064404 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8747. Min Act: -0.0001

Data Index: 450145 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8683. Min Act: -0.0001

Data Index: 827451 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8566. Min Act: -0.0001

Data Index: 1262515 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8356. Min Act: -0.0001

Data Index: 1193021 (C4 (Web Text))

Max Activating Token Index: 562