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

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

Neuron 4484 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.7680. Min Act: -0.0001

Data Index: 319463 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.7345. Min Act: -0.0001

Data Index: 741241 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.6320. Min Act: -0.0001

Data Index: 1615864 (Python Code)

Max Activating Token Index: 211

Text #3

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.8126. Min Act: -0.0001

Data Index: 1201433 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5959. Min Act: -0.0001

Data Index: 1238473 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.6839. Min Act: -0.0001

Data Index: 304753 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.6117. Min Act: -0.0001

Data Index: 665074 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.6126. Min Act: -0.0001

Data Index: 703654 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.6589. Min Act: -0.0001

Data Index: 819183 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.6432. Min Act: -0.0001

Data Index: 698284 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5966. Min Act: -0.0001

Data Index: 496551 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5097. Min Act: -0.0001

Data Index: 458777 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5023. Min Act: -0.0001

Data Index: 978019 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5848. Min Act: -0.0001

Data Index: 682958 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5188. Min Act: -0.0001

Data Index: 936225 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5786. Min Act: -0.0001

Data Index: 992622 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5991. Min Act: -0.0001

Data Index: 1069781 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5712. Min Act: -0.0001

Data Index: 420592 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5568. Min Act: -0.0001

Data Index: 1061768 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5077. Min Act: -0.0001

Data Index: 1057042 (C4 (Web Text))

Max Activating Token Index: 2