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

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

Neuron 4533 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0914. Min Act: -0.0000

Data Index: 281451 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0826. Min Act: -0.0000

Data Index: 197851 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0784. Min Act: -0.0000

Data Index: 694529 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0747. Min Act: -0.0000

Data Index: 743483 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0797. Min Act: -0.0000

Data Index: 711240 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0722. Min Act: -0.0000

Data Index: 885389 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0687. Min Act: -0.0000

Data Index: 932248 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0685. Min Act: -0.0001

Data Index: 160071 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1221780 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0700. Min Act: -0.0000

Data Index: 754305 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0655. Min Act: -0.0000

Data Index: 361954 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0591. Min Act: -0.0000

Data Index: 743125 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0628. Min Act: -0.0000

Data Index: 583640 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1103233 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0573. Min Act: -0.0000

Data Index: 425452 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0597. Min Act: -0.0000

Data Index: 760843 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0612. Min Act: -0.0000

Data Index: 970702 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0543. Min Act: -0.0000

Data Index: 455544 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0529. Min Act: -0.0000

Data Index: 111387 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0541. Min Act: -0.0000

Data Index: 848558 (C4 (Web Text))

Max Activating Token Index: 260