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

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

Neuron 3556 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.3628. Min Act: -0.0000

Data Index: 887682 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.4234. Min Act: -0.0000

Data Index: 868132 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2739. Min Act: -0.0000

Data Index: 1272776 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1121833 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.1702. Min Act: 0.0000

Data Index: 1030962 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.1142. Min Act: -0.0000

Data Index: 999965 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.0316. Min Act: -0.0000

Data Index: 299026 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1288912 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.0652. Min Act: -0.0000

Data Index: 682596 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9694. Min Act: -0.0000

Data Index: 268348 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9967. Min Act: -0.0000

Data Index: 870774 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9110. Min Act: -0.0000

Data Index: 489205 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1135170 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9732. Min Act: -0.0000

Data Index: 277396 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.8850. Min Act: -0.0000

Data Index: 193453 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1031034 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1058328 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.7957. Min Act: -0.0000

Data Index: 768559 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.8172. Min Act: 0.0000

Data Index: 793696 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1081390 (C4 (Web Text))

Max Activating Token Index: 688