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

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

Neuron 1268 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: 1.1423. Min Range: -1.1423

Max Act: 1.0631. Min Act: -0.0001

Data Index: 1584739 (Python Code)

Max Activating Token Index: 147

Text #1

Max Range: 1.1423. Min Range: -1.1423

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1531789 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 1.1423. Min Range: -1.1423

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1379577 (Python Code)

Max Activating Token Index: 759

Text #3

Max Range: 1.1423. Min Range: -1.1423

Max Act: 1.0546. Min Act: -0.0001

Data Index: 1656257 (Python Code)

Max Activating Token Index: 388

Text #4

Max Range: 1.1423. Min Range: -1.1423

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1500701 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9590. Min Act: -0.0001

Data Index: 1446054 (Python Code)

Max Activating Token Index: 372

Text #6

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1361332 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1523170 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8756. Min Act: -0.0001

Data Index: 1396162 (Python Code)

Max Activating Token Index: 723

Text #9

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1377769 (Python Code)

Max Activating Token Index: 509

Text #10

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1624893 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9226. Min Act: -0.0001

Data Index: 1527063 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9777. Min Act: -0.0001

Data Index: 1656527 (Python Code)

Max Activating Token Index: 798

Text #13

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1592669 (Python Code)

Max Activating Token Index: 852

Text #14

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9230. Min Act: -0.0001

Data Index: 1499253 (Python Code)

Max Activating Token Index: 498

Text #15

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1499120 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1435963 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9163. Min Act: -0.0001

Data Index: 1594748 (Python Code)

Max Activating Token Index: 934

Text #18

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1434218 (Python Code)

Max Activating Token Index: 653

Text #19

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1445201 (Python Code)

Max Activating Token Index: 931