Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5647 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1132148 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8074. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1014337 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8025. Min Act: -0.0000

Data Index: 810307 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7738. Min Act: -0.0000

Data Index: 313382 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6977. Min Act: -0.0000

Data Index: 710755 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7716. Min Act: -0.0000

Data Index: 596331 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7475. Min Act: -0.0000

Data Index: 260345 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6909. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6911. Min Act: -0.0000

Data Index: 80704 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1335802 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1061435 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6480. Min Act: -0.0000

Data Index: 893109 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6440. Min Act: 0.0000

Data Index: 1265123 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6736. Min Act: -0.0000

Data Index: 689900 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6258. Min Act: -0.0000

Data Index: 136449 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.6279. Min Act: -0.0000

Data Index: 468438 (C4 (Web Text))

Max Activating Token Index: 509