Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 768 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6677. Min Act: -0.0001

Data Index: 154795 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6858. Min Act: -0.0001

Data Index: 721055 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6883. Min Act: -0.0001

Data Index: 533817 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6608. Min Act: -0.0001

Data Index: 1174575 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6357. Min Act: 0.0000

Data Index: 698548 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5925. Min Act: -0.0001

Data Index: 243811 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5719. Min Act: -0.0001

Data Index: 142164 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5621. Min Act: -0.0001

Data Index: 1219424 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5794. Min Act: -0.0001

Data Index: 443339 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5293. Min Act: -0.0001

Data Index: 1011672 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5368. Min Act: -0.0001

Data Index: 323851 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1019787 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5380. Min Act: -0.0001

Data Index: 887641 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5453. Min Act: -0.0001

Data Index: 839522 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5215. Min Act: -0.0001

Data Index: 263974 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5181. Min Act: -0.0001

Data Index: 1235502 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5030. Min Act: -0.0001

Data Index: 594182 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5377. Min Act: -0.0001

Data Index: 879516 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5359. Min Act: -0.0000

Data Index: 333120 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5044. Min Act: -0.0001

Data Index: 1307988 (C4 (Web Text))

Max Activating Token Index: 146