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

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

Neuron 2739 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: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0001

Data Index: 539086 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1120313 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0512. Min Act: -0.0001

Data Index: 644616 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0519. Min Act: -0.0001

Data Index: 722163 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0406. Min Act: -0.0001

Data Index: 217229 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1230099 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0423. Min Act: -0.0001

Data Index: 599748 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1054015 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0443. Min Act: -0.0001

Data Index: 960829 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0340. Min Act: -0.0001

Data Index: 437200 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0377. Min Act: -0.0001

Data Index: 268876 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0435. Min Act: -0.0001

Data Index: 333455 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0442. Min Act: -0.0001

Data Index: 609669 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0422. Min Act: -0.0001

Data Index: 192183 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1056037 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0399. Min Act: -0.0001

Data Index: 67629 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0364. Min Act: -0.0001

Data Index: 531900 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0410. Min Act: -0.0001

Data Index: 952388 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0418. Min Act: -0.0001

Data Index: 100751 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0342. Min Act: -0.0001

Data Index: 657083 (C4 (Web Text))

Max Activating Token Index: 851