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

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

Neuron 760 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7803. Min Act: -0.0000

Data Index: 252137 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7824. Min Act: -0.0000

Data Index: 19136 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7319. Min Act: -0.0001

Data Index: 24061 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1017074 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7277. Min Act: -0.0000

Data Index: 832722 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7337. Min Act: -0.0000

Data Index: 344052 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7281. Min Act: -0.0001

Data Index: 45594 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7307. Min Act: -0.0000

Data Index: 915985 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1249148 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6354. Min Act: -0.0000

Data Index: 239057 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6615. Min Act: -0.0000

Data Index: 717624 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7040. Min Act: -0.0001

Data Index: 440668 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6313. Min Act: -0.0001

Data Index: 397039 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6526. Min Act: -0.0000

Data Index: 160720 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6338. Min Act: -0.0001

Data Index: 1318171 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1322862 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6414. Min Act: -0.0001

Data Index: 160703 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6460. Min Act: -0.0000

Data Index: 544672 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1216070 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1072072 (C4 (Web Text))

Max Activating Token Index: 98