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

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

Neuron 5521 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0001

Data Index: 145990 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1021624 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0595. Min Act: -0.0001

Data Index: 294105 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1335833 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0405. Min Act: -0.0002

Data Index: 314184 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0512. Min Act: -0.0001

Data Index: 237968 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0434. Min Act: -0.0002

Data Index: 641337 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0442. Min Act: -0.0001

Data Index: 204978 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1275656 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0377. Min Act: -0.0001

Data Index: 529061 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1053775 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0367. Min Act: -0.0001

Data Index: 705414 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0333. Min Act: -0.0001

Data Index: 238554 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0328. Min Act: -0.0001

Data Index: 389809 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0343. Min Act: -0.0001

Data Index: 687530 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0354. Min Act: -0.0001

Data Index: 129406 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0365. Min Act: -0.0001

Data Index: 567604 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1314336 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1162065 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0324. Min Act: -0.0001

Data Index: 938195 (C4 (Web Text))

Max Activating Token Index: 531