Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 800 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0006

Data Index: 1546900 (Python Code)

Max Activating Token Index: 407

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0621. Min Act: -0.0006

Data Index: 1414157 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0604. Min Act: -0.0006

Data Index: 1446053 (Python Code)

Max Activating Token Index: 405

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0598. Min Act: -0.0006

Data Index: 1388921 (Python Code)

Max Activating Token Index: 480

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0598. Min Act: -0.0006

Data Index: 1452781 (Python Code)

Max Activating Token Index: 371

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0607. Min Act: -0.0006

Data Index: 1575900 (Python Code)

Max Activating Token Index: 277

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0603. Min Act: -0.0006

Data Index: 1583604 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0573. Min Act: -0.0006

Data Index: 1611353 (Python Code)

Max Activating Token Index: 459

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0582. Min Act: -0.0006

Data Index: 1649203 (Python Code)

Max Activating Token Index: 414

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0577. Min Act: -0.0006

Data Index: 1616401 (Python Code)

Max Activating Token Index: 502

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0589. Min Act: -0.0006

Data Index: 1481615 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0573. Min Act: -0.0006

Data Index: 1569001 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0582. Min Act: -0.0006

Data Index: 1408643 (Python Code)

Max Activating Token Index: 550

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0543. Min Act: -0.0006

Data Index: 1360033 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0538. Min Act: -0.0006

Data Index: 1633634 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0528. Min Act: -0.0006

Data Index: 1437457 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0537. Min Act: -0.0006

Data Index: 1404548 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0549. Min Act: -0.0006

Data Index: 1565354 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0558. Min Act: -0.0006

Data Index: 1554868 (Python Code)

Max Activating Token Index: 420

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0582. Min Act: -0.0006

Data Index: 1420822 (Python Code)

Max Activating Token Index: 563