Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 86 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.5553. Min Act: -0.0000

Data Index: 270093 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.5420. Min Act: -0.0000

Data Index: 876349 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4984. Min Act: -0.0000

Data Index: 976714 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1299316 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4717. Min Act: -0.0000

Data Index: 189699 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4387. Min Act: -0.0000

Data Index: 103263 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1011902 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4159. Min Act: -0.0000

Data Index: 933962 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4083. Min Act: -0.0000

Data Index: 479566 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4305. Min Act: -0.0000

Data Index: 255526 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4413. Min Act: -0.0000

Data Index: 185751 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4266. Min Act: -0.0000

Data Index: 571737 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.3985. Min Act: -0.0000

Data Index: 30797 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1051019 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1234936 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1214530 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.3771. Min Act: -0.0000

Data Index: 766097 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1136411 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1131083 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.3704. Min Act: -0.0000

Data Index: 569965 (C4 (Web Text))

Max Activating Token Index: 57