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

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

Neuron 2165 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.3992. Min Act: -0.0001

Data Index: 752303 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.0774. Min Act: -0.0001

Data Index: 73734 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.0869. Min Act: -0.0001

Data Index: 229802 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.0186. Min Act: -0.0001

Data Index: 500853 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.0049. Min Act: -0.0000

Data Index: 696666 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9934. Min Act: -0.0001

Data Index: 1020494 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9424. Min Act: -0.0001

Data Index: 854019 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.0028. Min Act: -0.0001

Data Index: 720541 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8042. Min Act: -0.0001

Data Index: 413065 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8902. Min Act: -0.0001

Data Index: 222808 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9140. Min Act: -0.0000

Data Index: 610493 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9759. Min Act: -0.0001

Data Index: 857119 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8311. Min Act: -0.0001

Data Index: 953009 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9328. Min Act: -0.0001

Data Index: 1208838 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8989. Min Act: -0.0001

Data Index: 1020723 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1024829 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8608. Min Act: -0.0001

Data Index: 660795 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8556. Min Act: -0.0001

Data Index: 954052 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8307. Min Act: -0.0001

Data Index: 1107257 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8710. Min Act: -0.0001

Data Index: 182004 (C4 (Web Text))

Max Activating Token Index: 581