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

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

Neuron 3418 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1585527 (Python Code)

Max Activating Token Index: 616

Text #1

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1625834 (Python Code)

Max Activating Token Index: 215

Text #2

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1418901 (Python Code)

Max Activating Token Index: 761

Text #3

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1444138 (Python Code)

Max Activating Token Index: 118

Text #4

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1423351 (Python Code)

Max Activating Token Index: 228

Text #5

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1360501 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1470577 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1469907 (Python Code)

Max Activating Token Index: 219

Text #8

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1393333 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1543935 (Python Code)

Max Activating Token Index: 497

Text #10

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1488081 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1601833 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1599930 (Python Code)

Max Activating Token Index: 411

Text #13

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1596417 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1548937 (Python Code)

Max Activating Token Index: 593

Text #15

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1453647 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1422548 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1651834 (Python Code)

Max Activating Token Index: 753

Text #18

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1643786 (Python Code)

Max Activating Token Index: 81

Text #19

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1598701 (Python Code)

Max Activating Token Index: 154