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

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

Neuron 2847 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: 0.9431. Min Range: -0.9431

Max Act: 0.9431. Min Act: -0.0001

Data Index: 274274 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.8057. Min Act: -0.0001

Data Index: 641822 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.7214. Min Act: -0.0001

Data Index: 1153245 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6880. Min Act: -0.0001

Data Index: 400782 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6601. Min Act: -0.0001

Data Index: 1340477 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6702. Min Act: -0.0001

Data Index: 578321 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6405. Min Act: -0.0000

Data Index: 761748 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6561. Min Act: -0.0001

Data Index: 498269 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6677. Min Act: -0.0001

Data Index: 233317 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6393. Min Act: -0.0001

Data Index: 1244764 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6124. Min Act: -0.0001

Data Index: 333680 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5779. Min Act: -0.0001

Data Index: 184085 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5376. Min Act: -0.0001

Data Index: 961743 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5799. Min Act: -0.0001

Data Index: 881134 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5753. Min Act: -0.0001

Data Index: 148176 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5798. Min Act: -0.0001

Data Index: 1195627 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5234. Min Act: -0.0000

Data Index: 144601 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5393. Min Act: -0.0001

Data Index: 62556 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5359. Min Act: -0.0001

Data Index: 1221977 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5487. Min Act: -0.0001

Data Index: 575799 (C4 (Web Text))

Max Activating Token Index: 869