Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 452 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1249200 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0043. Min Act: -0.0003

Data Index: 992174 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0042. Min Act: -0.0003

Data Index: 793705 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0042. Min Act: -0.0003

Data Index: 510770 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0004

Data Index: 625988 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0004

Data Index: 357907 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0004

Data Index: 281338 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0004

Data Index: 361530 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0003

Data Index: 156564 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0003

Data Index: 571434 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0002

Data Index: 808259 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1447054 (Python Code)

Max Activating Token Index: 404

Text #12

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0003

Data Index: 516986 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0004

Data Index: 601373 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0004

Data Index: 173954 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0003

Data Index: 253893 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0004

Data Index: 674568 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0003

Data Index: 697491 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0004

Data Index: 546905 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0002

Data Index: 99008 (C4 (Web Text))

Max Activating Token Index: 796