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

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

Neuron 4050 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0732. Min Range: -2.0732

Max Act: 2.0732. Min Act: -0.0000

Data Index: 1564054 (Python Code)

Max Activating Token Index: 997

Text #1

Max Range: 2.0732. Min Range: -2.0732

Max Act: 2.0530. Min Act: -0.0000

Data Index: 1205878 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 2.0732. Min Range: -2.0732

Max Act: 2.0264. Min Act: -0.0000

Data Index: 954483 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.8440. Min Act: -0.0000

Data Index: 1409680 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.6863. Min Act: -0.0000

Data Index: 586337 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.7236. Min Act: -0.0000

Data Index: 464695 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.6933. Min Act: -0.0000

Data Index: 817588 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.5888. Min Act: -0.0000

Data Index: 1244991 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.7510. Min Act: -0.0000

Data Index: 39253 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.5525. Min Act: -0.0000

Data Index: 766143 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.5490. Min Act: -0.0000

Data Index: 665113 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.8142. Min Act: -0.0000

Data Index: 568203 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.5043. Min Act: -0.0000

Data Index: 914893 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.6014. Min Act: -0.0000

Data Index: 344145 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.6484. Min Act: -0.0000

Data Index: 661180 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.5319. Min Act: -0.0000

Data Index: 233244 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.5251. Min Act: -0.0000

Data Index: 60206 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.5059. Min Act: -0.0000

Data Index: 589790 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.5974. Min Act: -0.0000

Data Index: 725145 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 2.0732. Min Range: -2.0732

Max Act: 1.4942. Min Act: -0.0000

Data Index: 1607139 (Python Code)

Max Activating Token Index: 267