Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1202 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.4113. Min Act: -0.0001

Data Index: 1415513 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1604092 (Python Code)

Max Activating Token Index: 147

Text #2

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.2230. Min Act: -0.0001

Data Index: 1469018 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.2112. Min Act: -0.0001

Data Index: 1648442 (Python Code)

Max Activating Token Index: 751

Text #4

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0732. Min Act: -0.0001

Data Index: 1624669 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0971. Min Act: -0.0001

Data Index: 1453284 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1517714 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.1122. Min Act: -0.0001

Data Index: 1651731 (Python Code)

Max Activating Token Index: 443

Text #8

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0783. Min Act: -0.0001

Data Index: 1459595 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.1058. Min Act: -0.0001

Data Index: 1595135 (Python Code)

Max Activating Token Index: 441

Text #10

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0866. Min Act: -0.0001

Data Index: 1393060 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0542. Min Act: -0.0001

Data Index: 1405554 (Python Code)

Max Activating Token Index: 270

Text #12

Max Range: 1.4113. Min Range: -1.4113

Max Act: 0.9821. Min Act: -0.0001

Data Index: 1612318 (Python Code)

Max Activating Token Index: 360

Text #13

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0629. Min Act: -0.0001

Data Index: 1647184 (Python Code)

Max Activating Token Index: 125

Text #14

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0249. Min Act: -0.0001

Data Index: 1449463 (Python Code)

Max Activating Token Index: 445

Text #15

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0245. Min Act: -0.0001

Data Index: 1650032 (Python Code)

Max Activating Token Index: 403

Text #16

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1476055 (Python Code)

Max Activating Token Index: 697

Text #17

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0501. Min Act: -0.0001

Data Index: 1493628 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 1.4113. Min Range: -1.4113

Max Act: 0.9607. Min Act: -0.0001

Data Index: 1538401 (Python Code)

Max Activating Token Index: 884

Text #19

Max Range: 1.4113. Min Range: -1.4113

Max Act: 0.9502. Min Act: -0.0001

Data Index: 1526961 (Python Code)

Max Activating Token Index: 895