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

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

Neuron 5037 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1088. Min Range: -1.1088

Max Act: 1.1088. Min Act: -0.0001

Data Index: 928993 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.9695. Min Act: -0.0001

Data Index: 1151893 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.9738. Min Act: -0.0001

Data Index: 739595 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1240042 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8184. Min Act: -0.0000

Data Index: 702571 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8501. Min Act: -0.0001

Data Index: 172943 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8878. Min Act: -0.0001

Data Index: 755800 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1022176 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8470. Min Act: -0.0001

Data Index: 360220 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1527494 (Python Code)

Max Activating Token Index: 1005

Text #10

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8601. Min Act: -0.0001

Data Index: 833982 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8615. Min Act: -0.0001

Data Index: 453474 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8055. Min Act: -0.0001

Data Index: 1204954 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.7815. Min Act: -0.0001

Data Index: 103664 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1166791 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1233323 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.9132. Min Act: -0.0001

Data Index: 46265 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.7395. Min Act: -0.0001

Data Index: 934150 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.6877. Min Act: -0.0001

Data Index: 306780 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 1.1088. Min Range: -1.1088

Max Act: 0.7464. Min Act: -0.0001

Data Index: 330897 (C4 (Web Text))

Max Activating Token Index: 151