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

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

Neuron 4766 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3173. Min Range: -1.3173

Max Act: 1.3173. Min Act: -0.0000

Data Index: 1118227 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.3173. Min Range: -1.3173

Max Act: 1.2733. Min Act: -0.0000

Data Index: 22547 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 1.3173. Min Range: -1.3173

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1322405 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.3173. Min Range: -1.3173

Max Act: 1.2396. Min Act: -0.0000

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.3173. Min Range: -1.3173

Max Act: 1.0886. Min Act: -0.0000

Data Index: 1306601 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1118581 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.3173. Min Range: -1.3173

Max Act: 1.0276. Min Act: -0.0000

Data Index: 246792 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9602. Min Act: -0.0000

Data Index: 179284 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1428105 (Python Code)

Max Activating Token Index: 912

Text #9

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1053940 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9359. Min Act: -0.0000

Data Index: 337423 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9235. Min Act: -0.0000

Data Index: 495487 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1045509 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9373. Min Act: -0.0000

Data Index: 254449 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1289802 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9085. Min Act: -0.0000

Data Index: 539889 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8957. Min Act: -0.0000

Data Index: 457155 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8580. Min Act: -0.0000

Data Index: 9468 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1234030 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1122367 (C4 (Web Text))

Max Activating Token Index: 87