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

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

Neuron 2371 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.1785. Min Act: -0.0001

Data Index: 270409 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.0750. Min Act: -0.0001

Data Index: 382797 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.0542. Min Act: -0.0000

Data Index: 746560 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.0033. Min Act: -0.0001

Data Index: 534128 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9297. Min Act: -0.0000

Data Index: 909219 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8908. Min Act: -0.0001

Data Index: 533035 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9095. Min Act: -0.0001

Data Index: 245554 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8727. Min Act: -0.0000

Data Index: 354037 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9042. Min Act: -0.0001

Data Index: 573493 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9018. Min Act: -0.0001

Data Index: 1195402 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1086887 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8625. Min Act: -0.0000

Data Index: 484140 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8060. Min Act: -0.0001

Data Index: 393245 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1280283 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8591. Min Act: -0.0001

Data Index: 445903 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8584. Min Act: -0.0001

Data Index: 1064048 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1011916 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7770. Min Act: -0.0000

Data Index: 726229 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1202716 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1322424 (C4 (Web Text))

Max Activating Token Index: 714