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

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

Neuron 3587 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7972. Min Act: -0.0000

Data Index: 843398 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.8655. Min Act: -0.0000

Data Index: 256157 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.8390. Min Act: -0.0000

Data Index: 781473 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7358. Min Act: -0.0000

Data Index: 381362 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7606. Min Act: -0.0000

Data Index: 831267 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7275. Min Act: -0.0000

Data Index: 13972 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7870. Min Act: -0.0000

Data Index: 185439 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1331558 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1349986 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.6949. Min Act: -0.0000

Data Index: 57128 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1103222 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1260813 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1096575 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1244316 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7122. Min Act: -0.0000

Data Index: 629341 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1063088 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.6686. Min Act: -0.0000

Data Index: 238397 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7041. Min Act: -0.0000

Data Index: 168649 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.6740. Min Act: -0.0000

Data Index: 22681 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.6897. Min Act: -0.0000

Data Index: 182824 (C4 (Web Text))

Max Activating Token Index: 567