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

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

Neuron 226 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: 0.5324. Min Range: -0.5324

Max Act: 0.5324. Min Act: -0.0001

Data Index: 376871 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.5104. Min Act: -0.0000

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4963. Min Act: -0.0000

Data Index: 900071 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4755. Min Act: -0.0000

Data Index: 870252 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4829. Min Act: -0.0000

Data Index: 262538 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4283. Min Act: -0.0000

Data Index: 963954 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4769. Min Act: -0.0000

Data Index: 18904 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1223130 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4291. Min Act: -0.0000

Data Index: 119771 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4348. Min Act: -0.0000

Data Index: 767556 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4290. Min Act: -0.0001

Data Index: 1071278 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1117643 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3907. Min Act: -0.0000

Data Index: 395531 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4021. Min Act: -0.0000

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3938. Min Act: -0.0000

Data Index: 742612 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1328499 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1034103 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3834. Min Act: -0.0000

Data Index: 400917 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1249861 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3328. Min Act: -0.0000

Data Index: 868863 (C4 (Web Text))

Max Activating Token Index: 992