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

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

Neuron 3051 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: 1.5558. Min Range: -1.5558

Max Act: 1.5558. Min Act: -0.0000

Data Index: 70256 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 1.5558. Min Range: -1.5558

Max Act: 1.4381. Min Act: -0.0000

Data Index: 448617 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 1.5558. Min Range: -1.5558

Max Act: 1.1835. Min Act: -0.0000

Data Index: 930564 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.5558. Min Range: -1.5558

Max Act: 1.1037. Min Act: -0.0000

Data Index: 242116 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.9456. Min Act: -0.0000

Data Index: 102306 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1019908 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.8703. Min Act: -0.0000

Data Index: 972362 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.7821. Min Act: -0.0000

Data Index: 110141 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1120313 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1186263 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.8372. Min Act: -0.0000

Data Index: 495934 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.8329. Min Act: -0.0000

Data Index: 713258 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.7973. Min Act: -0.0001

Data Index: 1324660 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.8195. Min Act: -0.0000

Data Index: 235336 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1315252 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.6921. Min Act: -0.0001

Data Index: 1081033 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.7489. Min Act: -0.0000

Data Index: 137674 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1215004 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.7447. Min Act: -0.0000

Data Index: 503965 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.5558. Min Range: -1.5558

Max Act: 0.7545. Min Act: -0.0000

Data Index: 483534 (C4 (Web Text))

Max Activating Token Index: 756