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

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

Neuron 1640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2903. Min Act: -0.0000

Data Index: 653274 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1109313 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1069917 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2605. Min Act: -0.0000

Data Index: 427101 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2542. Min Act: -0.0000

Data Index: 649645 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2504. Min Act: -0.0000

Data Index: 457276 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2504. Min Act: -0.0000

Data Index: 932668 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2460. Min Act: -0.0000

Data Index: 902985 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2453. Min Act: -0.0000

Data Index: 430429 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2414. Min Act: -0.0000

Data Index: 399280 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2872. Min Act: -0.0000

Data Index: 424894 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2481. Min Act: -0.0000

Data Index: 85653 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2297. Min Act: -0.0000

Data Index: 828424 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2199. Min Act: -0.0000

Data Index: 673336 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2340. Min Act: -0.0000

Data Index: 916674 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2390. Min Act: -0.0000

Data Index: 488160 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2311. Min Act: -0.0000

Data Index: 488963 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2290. Min Act: -0.0000

Data Index: 185097 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1144414 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2222. Min Act: -0.0000

Data Index: 883527 (C4 (Web Text))

Max Activating Token Index: 806