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

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

Neuron 3 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1600851 (Python Code)

Max Activating Token Index: 903

Text #1

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1410869 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1494096 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1645519 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1583260 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1524489 (Python Code)

Max Activating Token Index: 1014

Text #6

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1618845 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1456125 (Python Code)

Max Activating Token Index: 930

Text #8

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1546836 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1463708 (Python Code)

Max Activating Token Index: 1002

Text #10

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1364048 (Python Code)

Max Activating Token Index: 245

Text #11

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1529255 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1537280 (Python Code)

Max Activating Token Index: 589

Text #13

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1475578 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1437586 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1637469 (Python Code)

Max Activating Token Index: 806

Text #16

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1426224 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1433602 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1572280 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1487312 (Python Code)

Max Activating Token Index: 377