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

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

Neuron 3374 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1520. Min Range: -1.1520

Max Act: 1.0823. Min Act: -0.0000

Data Index: 582589 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.9043. Min Act: -0.0000

Data Index: 180098 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 1.1520. Min Range: -1.1520

Max Act: 1.1022. Min Act: -0.0000

Data Index: 176979 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.1520. Min Range: -1.1520

Max Act: 1.1148. Min Act: -0.0000

Data Index: 327552 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 1.1520. Min Range: -1.1520

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1027948 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.1520. Min Range: -1.1520

Max Act: 1.0273. Min Act: -0.0001

Data Index: 845654 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.9511. Min Act: -0.0001

Data Index: 106261 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.8877. Min Act: -0.0001

Data Index: 1053484 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.1520. Min Range: -1.1520

Max Act: 1.0483. Min Act: -0.0000

Data Index: 787388 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.9621. Min Act: -0.0000

Data Index: 291653 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.8695. Min Act: -0.0000

Data Index: 846319 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 1.1520. Min Range: -1.1520

Max Act: 1.0672. Min Act: -0.0001

Data Index: 1199725 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.9353. Min Act: -0.0000

Data Index: 82477 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.9093. Min Act: -0.0000

Data Index: 532936 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.9634. Min Act: -0.0000

Data Index: 155320 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 1.1520. Min Range: -1.1520

Max Act: 1.1520. Min Act: -0.0000

Data Index: 652275 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1272503 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.1520. Min Range: -1.1520

Max Act: 0.9474. Min Act: -0.0001

Data Index: 1583375 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 1.1520. Min Range: -1.1520

Max Act: 1.0118. Min Act: -0.0001

Data Index: 690477 (C4 (Web Text))

Max Activating Token Index: 331