Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2416 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.9556. Min Act: -0.0001

Data Index: 174493 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.9922. Min Act: -0.0001

Data Index: 1293567 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.9211. Min Act: -0.0001

Data Index: 1169108 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.9486. Min Act: -0.0001

Data Index: 576775 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 1.0065. Min Range: -1.0065

Max Act: 1.0065. Min Act: -0.0001

Data Index: 280549 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.9483. Min Act: -0.0001

Data Index: 126853 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.9191. Min Act: -0.0001

Data Index: 341675 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8766. Min Act: -0.0001

Data Index: 909536 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8658. Min Act: -0.0001

Data Index: 1079934 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8565. Min Act: -0.0001

Data Index: 611801 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8774. Min Act: -0.0001

Data Index: 112757 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8386. Min Act: -0.0001

Data Index: 27932 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.7836. Min Act: -0.0001

Data Index: 1128324 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8475. Min Act: -0.0001

Data Index: 59836 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8789. Min Act: -0.0001

Data Index: 265564 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8264. Min Act: -0.0001

Data Index: 610730 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8248. Min Act: -0.0001

Data Index: 628450 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1267429 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8405. Min Act: -0.0001

Data Index: 38872 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.8563. Min Act: -0.0001

Data Index: 1050346 (C4 (Web Text))

Max Activating Token Index: 511