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

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

Neuron 2522 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.8008. Min Act: -0.0000

Data Index: 618526 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.6022. Min Act: -0.0000

Data Index: 465496 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.3528. Min Act: -0.0000

Data Index: 1028322 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.4017. Min Act: -0.0000

Data Index: 283911 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.0692. Min Act: -0.0000

Data Index: 466521 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.7448. Min Act: -0.0000

Data Index: 787628 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.7741. Min Act: -0.0000

Data Index: 44939 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.9506. Min Act: -0.0000

Data Index: 239731 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.9546. Min Act: -0.0000

Data Index: 83000 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.9409. Min Act: -0.0000

Data Index: 460783 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.8809. Min Act: -0.0000

Data Index: 808080 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.9786. Min Act: -0.0000

Data Index: 16388 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.8067. Min Act: -0.0000

Data Index: 1185238 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.4457. Min Act: -0.0000

Data Index: 1127839 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.7623. Min Act: -0.0000

Data Index: 827162 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.4281. Min Act: -0.0000

Data Index: 1345502 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.5721. Min Act: -0.0000

Data Index: 293242 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.5727. Min Act: -0.0000

Data Index: 177911 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.8716. Min Act: -0.0000

Data Index: 1062825 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 4.8008. Min Range: -4.8008

Max Act: 3.5212. Min Act: -0.0000

Data Index: 574328 (C4 (Web Text))

Max Activating Token Index: 769