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

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

Neuron 1784 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1474545 (Python Code)

Max Activating Token Index: 620

Text #1

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1540974 (Python Code)

Max Activating Token Index: 398

Text #2

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1445917 (Python Code)

Max Activating Token Index: 605

Text #3

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1360546 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1560968 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1563198 (Python Code)

Max Activating Token Index: 489

Text #6

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1585023 (Python Code)

Max Activating Token Index: 572

Text #7

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1520250 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1494418 (Python Code)

Max Activating Token Index: 707

Text #9

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1573752 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1489563 (Python Code)

Max Activating Token Index: 549

Text #11

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1551715 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7816. Min Act: -0.0001

Data Index: 1437882 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1489295 (Python Code)

Max Activating Token Index: 859

Text #14

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1588030 (Python Code)

Max Activating Token Index: 362

Text #15

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1528839 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1631930 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1625296 (Python Code)

Max Activating Token Index: 393

Text #18

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1508307 (Python Code)

Max Activating Token Index: 584

Text #19

Max Range: 0.8694. Min Range: -0.8694

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1528600 (Python Code)

Max Activating Token Index: 314