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

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

Neuron 5074 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: 1.1507. Min Range: -1.1507

Max Act: 1.0434. Min Act: -0.0001

Data Index: 167852 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0152. Min Act: -0.0001

Data Index: 1080719 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.1507. Min Act: -0.0001

Data Index: 143902 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9866. Min Act: -0.0001

Data Index: 937677 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0345. Min Act: -0.0001

Data Index: 672496 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7812. Min Act: -0.0001

Data Index: 311144 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9164. Min Act: -0.0001

Data Index: 754773 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9105. Min Act: -0.0001

Data Index: 479790 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8832. Min Act: -0.0001

Data Index: 509720 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8499. Min Act: -0.0001

Data Index: 791969 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7907. Min Act: -0.0001

Data Index: 154709 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8148. Min Act: -0.0001

Data Index: 560458 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8359. Min Act: -0.0001

Data Index: 1178574 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7379. Min Act: -0.0001

Data Index: 1171861 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7139. Min Act: -0.0001

Data Index: 873961 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8263. Min Act: -0.0001

Data Index: 325484 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8476. Min Act: -0.0001

Data Index: 1330880 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8672. Min Act: -0.0001

Data Index: 504110 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8387. Min Act: -0.0001

Data Index: 1294626 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8191. Min Act: -0.0001

Data Index: 176713 (C4 (Web Text))

Max Activating Token Index: 607