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

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

Neuron 1096 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: 0.6906. Min Range: -0.6906

Max Act: 0.6760. Min Act: -0.0000

Data Index: 6473 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.6906. Min Act: -0.0000

Data Index: 785495 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.6079. Min Act: -0.0000

Data Index: 175811 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.6220. Min Act: -0.0000

Data Index: 454286 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5603. Min Act: -0.0000

Data Index: 213032 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1255136 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5731. Min Act: -0.0000

Data Index: 669582 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1105796 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5869. Min Act: -0.0000

Data Index: 676214 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1372463 (Python Code)

Max Activating Token Index: 418

Text #10

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5775. Min Act: -0.0000

Data Index: 909767 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5771. Min Act: -0.0000

Data Index: 840788 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5780. Min Act: -0.0000

Data Index: 785420 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1292436 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5492. Min Act: -0.0000

Data Index: 223377 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5618. Min Act: -0.0000

Data Index: 850281 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1367656 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1596653 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1396502 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5408. Min Act: -0.0000

Data Index: 604680 (C4 (Web Text))

Max Activating Token Index: 425