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

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

Neuron 5069 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3023. Min Range: -4.3023

Max Act: 4.3023. Min Act: -0.0000

Data Index: 1640540 (Python Code)

Max Activating Token Index: 845

Text #1

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.7146. Min Act: -0.0000

Data Index: 1493434 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.8946. Min Act: -0.0000

Data Index: 1518745 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.8866. Min Act: -0.0000

Data Index: 1568468 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.9265. Min Act: -0.0000

Data Index: 1582289 (Python Code)

Max Activating Token Index: 899

Text #5

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.8665. Min Act: -0.0000

Data Index: 1410718 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.6160. Min Act: -0.0000

Data Index: 1388120 (Python Code)

Max Activating Token Index: 695

Text #7

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.5954. Min Act: -0.0000

Data Index: 1508547 (Python Code)

Max Activating Token Index: 526

Text #8

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.8367. Min Act: -0.0000

Data Index: 1542472 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.4532. Min Act: -0.0000

Data Index: 1652611 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.4813. Min Act: -0.0000

Data Index: 1396004 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.4844. Min Act: -0.0000

Data Index: 1423668 (Python Code)

Max Activating Token Index: 803

Text #12

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.3227. Min Act: -0.0000

Data Index: 1457911 (Python Code)

Max Activating Token Index: 879

Text #13

Max Range: 4.3023. Min Range: -4.3023

Max Act: 3.4496. Min Act: -0.0000

Data Index: 1646507 (Python Code)

Max Activating Token Index: 790

Text #14

Max Range: 4.3023. Min Range: -4.3023

Max Act: 2.7061. Min Act: -0.0000

Data Index: 1513477 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 4.3023. Min Range: -4.3023

Max Act: 2.5221. Min Act: -0.0000

Data Index: 1557644 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 4.3023. Min Range: -4.3023

Max Act: 2.5196. Min Act: -0.0000

Data Index: 1652456 (Python Code)

Max Activating Token Index: 787

Text #17

Max Range: 4.3023. Min Range: -4.3023

Max Act: 2.5091. Min Act: -0.0000

Data Index: 1635587 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 4.3023. Min Range: -4.3023

Max Act: 2.6875. Min Act: -0.0000

Data Index: 1591928 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 4.3023. Min Range: -4.3023

Max Act: 2.6006. Min Act: -0.0000

Data Index: 1548293 (Python Code)

Max Activating Token Index: 462