Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2437 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.6589. Min Act: -0.0001

Data Index: 658423 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4314. Min Act: -0.0001

Data Index: 391460 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.5461. Min Act: -0.0001

Data Index: 765088 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.2101. Min Act: -0.0001

Data Index: 662550 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.4768. Min Act: -0.0001

Data Index: 724671 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.2785. Min Act: -0.0001

Data Index: 599052 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.2506. Min Act: -0.0001

Data Index: 226391 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.2210. Min Act: -0.0001

Data Index: 389835 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.1373. Min Act: -0.0001

Data Index: 877473 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.1531. Min Act: -0.0001

Data Index: 1012980 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.1448. Min Act: -0.0001

Data Index: 562493 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.1245. Min Act: -0.0001

Data Index: 1109125 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.0901. Min Act: -0.0001

Data Index: 429759 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.0865. Min Act: -0.0001

Data Index: 228258 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 3.6589. Min Range: -3.6589

Max Act: 3.0485. Min Act: -0.0001

Data Index: 568387 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 3.6589. Min Range: -3.6589

Max Act: 2.9020. Min Act: -0.0001

Data Index: 765916 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 3.6589. Min Range: -3.6589

Max Act: 2.8857. Min Act: -0.0001

Data Index: 507625 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 3.6589. Min Range: -3.6589

Max Act: 2.8451. Min Act: -0.0001

Data Index: 802997 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 3.6589. Min Range: -3.6589

Max Act: 2.7812. Min Act: -0.0001

Data Index: 106785 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 3.6589. Min Range: -3.6589

Max Act: 2.9101. Min Act: -0.0001

Data Index: 1440697 (Python Code)

Max Activating Token Index: 4