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

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

Neuron 4944 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7570. Min Act: -0.0001

Data Index: 819650 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7744. Min Act: -0.0001

Data Index: 805898 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7294. Min Act: -0.0001

Data Index: 1262107 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7364. Min Act: -0.0001

Data Index: 448654 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6915. Min Act: -0.0001

Data Index: 678068 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1134222 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7085. Min Act: -0.0001

Data Index: 571430 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7113. Min Act: -0.0001

Data Index: 1180167 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1337970 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6481. Min Act: -0.0001

Data Index: 735628 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7117. Min Act: -0.0001

Data Index: 676454 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6068. Min Act: -0.0001

Data Index: 38429 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6129. Min Act: -0.0001

Data Index: 685443 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7100. Min Act: -0.0001

Data Index: 682134 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6974. Min Act: -0.0001

Data Index: 38374 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6881. Min Act: -0.0001

Data Index: 1052941 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6694. Min Act: -0.0001

Data Index: 110181 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6514. Min Act: -0.0001

Data Index: 799018 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6274. Min Act: -0.0001

Data Index: 240592 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7078. Min Act: -0.0001

Data Index: 335346 (C4 (Web Text))

Max Activating Token Index: 247