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

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

Neuron 3092 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1646. Min Range: -1.1646

Max Act: 1.1646. Min Act: -0.0001

Data Index: 1037961 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9600. Min Act: -0.0001

Data Index: 1067325 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.1646. Min Range: -1.1646

Max Act: 1.0064. Min Act: -0.0001

Data Index: 1088927 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 1.1646. Min Range: -1.1646

Max Act: 1.0187. Min Act: -0.0001

Data Index: 55681 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9319. Min Act: -0.0001

Data Index: 758693 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8336. Min Act: -0.0001

Data Index: 649658 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8814. Min Act: -0.0001

Data Index: 73606 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9559. Min Act: -0.0001

Data Index: 302081 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8850. Min Act: -0.0001

Data Index: 335549 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9052. Min Act: -0.0001

Data Index: 1275855 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9214. Min Act: -0.0001

Data Index: 546412 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8947. Min Act: -0.0001

Data Index: 1000606 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8609. Min Act: -0.0001

Data Index: 217848 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9685. Min Act: -0.0001

Data Index: 226233 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8596. Min Act: -0.0001

Data Index: 969658 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8605. Min Act: -0.0001

Data Index: 790173 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8321. Min Act: -0.0001

Data Index: 524713 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9092. Min Act: -0.0001

Data Index: 956624 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8789. Min Act: -0.0001

Data Index: 256313 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8942. Min Act: -0.0001

Data Index: 482558 (C4 (Web Text))

Max Activating Token Index: 251