Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2530 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0860. Min Range: -1.0860

Max Act: 1.0860. Min Act: -0.0001

Data Index: 427610 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.8853. Min Act: -0.0001

Data Index: 770999 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.8522. Min Act: -0.0001

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.9254. Min Act: -0.0001

Data Index: 858124 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.7350. Min Act: -0.0001

Data Index: 720139 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.7780. Min Act: -0.0001

Data Index: 1279943 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.7280. Min Act: -0.0001

Data Index: 375252 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.7357. Min Act: -0.0001

Data Index: 531886 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.7349. Min Act: -0.0001

Data Index: 457532 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.7057. Min Act: -0.0001

Data Index: 660475 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6583. Min Act: -0.0001

Data Index: 599411 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6974. Min Act: -0.0001

Data Index: 1259599 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6405. Min Act: -0.0001

Data Index: 586607 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6708. Min Act: -0.0001

Data Index: 421907 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6828. Min Act: -0.0001

Data Index: 315483 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6908. Min Act: -0.0001

Data Index: 78999 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6431. Min Act: -0.0001

Data Index: 695213 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6801. Min Act: -0.0001

Data Index: 965770 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6729. Min Act: -0.0001

Data Index: 18830 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.5539. Min Act: -0.0001

Data Index: 20102 (C4 (Web Text))

Max Activating Token Index: 209