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

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

Neuron 3618 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: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1016935 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0602. Min Act: -0.0000

Data Index: 736446 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0623. Min Act: -0.0000

Data Index: 250901 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0582. Min Act: -0.0001

Data Index: 460584 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0581. Min Act: -0.0000

Data Index: 242939 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0537. Min Act: -0.0000

Data Index: 386038 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1122793 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0557. Min Act: -0.0000

Data Index: 379808 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1007034 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0543. Min Act: -0.0000

Data Index: 400922 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1254427 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0526. Min Act: -0.0000

Data Index: 53471 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0479. Min Act: -0.0000

Data Index: 10425 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1019567 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0496. Min Act: -0.0000

Data Index: 350869 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0527. Min Act: -0.0000

Data Index: 860266 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1287969 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0503. Min Act: -0.0000

Data Index: 987585 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0498. Min Act: -0.0000

Data Index: 417725 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0486. Min Act: -0.0000

Data Index: 653255 (C4 (Web Text))

Max Activating Token Index: 460