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

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

Neuron 4849 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: 4.8640. Min Range: -4.8640

Max Act: 4.4524. Min Act: -0.0001

Data Index: 1432857 (Python Code)

Max Activating Token Index: 343

Text #1

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.5157. Min Act: -0.0001

Data Index: 1456962 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.8640. Min Act: -0.0001

Data Index: 1626262 (Python Code)

Max Activating Token Index: 407

Text #3

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.1805. Min Act: -0.0001

Data Index: 1467728 (Python Code)

Max Activating Token Index: 437

Text #4

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.9521. Min Act: -0.0001

Data Index: 1571879 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.0219. Min Act: -0.0001

Data Index: 1541566 (Python Code)

Max Activating Token Index: 526

Text #6

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.4546. Min Act: -0.0001

Data Index: 1419655 (Python Code)

Max Activating Token Index: 912

Text #7

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.5451. Min Act: -0.0000

Data Index: 1562314 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.5260. Min Act: -0.0001

Data Index: 1523823 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.5351. Min Act: -0.0001

Data Index: 1452289 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.4615. Min Act: -0.0000

Data Index: 1529398 (Python Code)

Max Activating Token Index: 421

Text #11

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.2681. Min Act: -0.0000

Data Index: 1528904 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.2451. Min Act: -0.0000

Data Index: 1541045 (Python Code)

Max Activating Token Index: 400

Text #13

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.0769. Min Act: -0.0001

Data Index: 1588397 (Python Code)

Max Activating Token Index: 696

Text #14

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.3848. Min Act: -0.0000

Data Index: 1600802 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.1898. Min Act: -0.0000

Data Index: 1535593 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.4955. Min Act: -0.0000

Data Index: 1613687 (Python Code)

Max Activating Token Index: 663

Text #17

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.4772. Min Act: -0.0001

Data Index: 1598184 (Python Code)

Max Activating Token Index: 817

Text #18

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.4602. Min Act: -0.0000

Data Index: 1622262 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 4.8640. Min Range: -4.8640

Max Act: 3.1287. Min Act: -0.0000

Data Index: 1400826 (Python Code)

Max Activating Token Index: 435