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

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

Neuron 2606 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2365. Min Range: -2.2365

Max Act: 2.2365. Min Act: -0.0001

Data Index: 1634602 (Python Code)

Max Activating Token Index: 53

Text #1

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.9718. Min Act: -0.0000

Data Index: 1591401 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 2.2365. Min Range: -2.2365

Max Act: 2.1486. Min Act: -0.0000

Data Index: 1652791 (Python Code)

Max Activating Token Index: 114

Text #3

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.9791. Min Act: -0.0000

Data Index: 1461533 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.7777. Min Act: -0.0000

Data Index: 1363307 (Python Code)

Max Activating Token Index: 320

Text #5

Max Range: 2.2365. Min Range: -2.2365

Max Act: 2.0874. Min Act: -0.0000

Data Index: 1602468 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.7791. Min Act: -0.0000

Data Index: 1378720 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.7666. Min Act: -0.0000

Data Index: 1551914 (Python Code)

Max Activating Token Index: 364

Text #8

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.7679. Min Act: -0.0000

Data Index: 1602937 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.8111. Min Act: -0.0000

Data Index: 1568826 (Python Code)

Max Activating Token Index: 528

Text #10

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.7411. Min Act: -0.0000

Data Index: 1472249 (Python Code)

Max Activating Token Index: 500

Text #11

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.7141. Min Act: -0.0000

Data Index: 1516639 (Python Code)

Max Activating Token Index: 235

Text #12

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.7742. Min Act: -0.0000

Data Index: 1363464 (Python Code)

Max Activating Token Index: 989

Text #13

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.8211. Min Act: -0.0000

Data Index: 1623820 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.8161. Min Act: -0.0000

Data Index: 1521452 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.6154. Min Act: -0.0001

Data Index: 1458204 (Python Code)

Max Activating Token Index: 147

Text #16

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.7103. Min Act: -0.0000

Data Index: 1363329 (Python Code)

Max Activating Token Index: 756

Text #17

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1630704 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.7947. Min Act: -0.0000

Data Index: 1453394 (Python Code)

Max Activating Token Index: 215

Text #19

Max Range: 2.2365. Min Range: -2.2365

Max Act: 1.5910. Min Act: -0.0001

Data Index: 1595398 (Python Code)

Max Activating Token Index: 41