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

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

Neuron 5480 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.2900. Min Act: -0.0000

Data Index: 1481514 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1229. Min Act: -0.0000

Data Index: 1525490 (Python Code)

Max Activating Token Index: 352

Text #2

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.8846. Min Act: -0.0000

Data Index: 1546712 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.8810. Min Act: -0.0000

Data Index: 1414306 (Python Code)

Max Activating Token Index: 594

Text #4

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.8570. Min Act: -0.0000

Data Index: 1523181 (Python Code)

Max Activating Token Index: 189

Text #5

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.6115. Min Act: -0.0000

Data Index: 1620987 (Python Code)

Max Activating Token Index: 155

Text #6

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.5849. Min Act: -0.0000

Data Index: 1422597 (Python Code)

Max Activating Token Index: 288

Text #7

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.6495. Min Act: -0.0000

Data Index: 1612584 (Python Code)

Max Activating Token Index: 891

Text #8

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.5379. Min Act: -0.0000

Data Index: 1504178 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.4578. Min Act: -0.0000

Data Index: 1470946 (Python Code)

Max Activating Token Index: 912

Text #10

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.2490. Min Act: -0.0000

Data Index: 1644275 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.0765. Min Act: -0.0000

Data Index: 1515808 (Python Code)

Max Activating Token Index: 130

Text #12

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.1676. Min Act: -0.0000

Data Index: 1407156 (Python Code)

Max Activating Token Index: 535

Text #13

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.1365. Min Act: -0.0000

Data Index: 1461408 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.0897. Min Act: -0.0000

Data Index: 1561124 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.3133. Min Act: -0.0000

Data Index: 1548269 (Python Code)

Max Activating Token Index: 282

Text #16

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.0595. Min Act: -0.0000

Data Index: 1447948 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 3.2900. Min Range: -3.2900

Max Act: 2.0380. Min Act: -0.0000

Data Index: 1553947 (Python Code)

Max Activating Token Index: 967

Text #18

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.8074. Min Act: -0.0000

Data Index: 1397634 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 3.2900. Min Range: -3.2900

Max Act: 1.8736. Min Act: -0.0000

Data Index: 1442026 (Python Code)

Max Activating Token Index: 117