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

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

Neuron 471 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.5432. Min Act: 0.0001

Data Index: 1233245 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.4114. Min Act: 0.0000

Data Index: 938061 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.3316. Min Act: -0.0000

Data Index: 516067 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.3244. Min Act: -0.0000

Data Index: 944725 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.2285. Min Act: 0.0000

Data Index: 736514 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1433. Min Act: 0.0000

Data Index: 1044443 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.2625. Min Act: 0.0000

Data Index: 47380 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.2058. Min Act: 0.0000

Data Index: 583835 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1164030 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1088. Min Act: -0.0000

Data Index: 546804 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1110849 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0248. Min Act: -0.0000

Data Index: 187935 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0580. Min Act: -0.0000

Data Index: 990652 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.8282. Min Act: -0.0000

Data Index: 90457 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9340. Min Act: -0.0000

Data Index: 919445 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9186. Min Act: -0.0000

Data Index: 171034 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9074. Min Act: -0.0000

Data Index: 112719 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0336. Min Act: 0.0001

Data Index: 247965 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.7686. Min Act: -0.0000

Data Index: 543488 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.8512. Min Act: -0.0000

Data Index: 31543 (C4 (Web Text))

Max Activating Token Index: 971