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

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

Neuron 353 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.7018. Min Act: -0.0000

Data Index: 1314670 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.7499. Min Act: -0.0000

Data Index: 683893 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.7234. Min Act: -0.0000

Data Index: 882819 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.5591. Min Act: -0.0000

Data Index: 395150 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.3077. Min Act: -0.0000

Data Index: 35351 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1010809 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.2105. Min Act: -0.0000

Data Index: 101863 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.2287. Min Act: -0.0000

Data Index: 478756 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.1770. Min Act: -0.0000

Data Index: 252221 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.1326. Min Act: -0.0000

Data Index: 187240 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.1836. Min Act: -0.0000

Data Index: 620878 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.1214. Min Act: -0.0000

Data Index: 522417 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.1148. Min Act: 0.0000

Data Index: 1077491 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1117450 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.1821. Min Act: -0.0000

Data Index: 489255 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.0590. Min Act: -0.0000

Data Index: 43273 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1127316 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.0905. Min Act: -0.0000

Data Index: 265470 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.9942. Min Act: -0.0000

Data Index: 789905 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.0287. Min Act: -0.0000

Data Index: 937535 (C4 (Web Text))

Max Activating Token Index: 88