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

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

Neuron 2432 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5533. Min Range: -2.5533

Max Act: 2.5533. Min Act: -0.0000

Data Index: 666629 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 2.5533. Min Range: -2.5533

Max Act: 2.1727. Min Act: -0.0000

Data Index: 493141 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 2.5533. Min Range: -2.5533

Max Act: 2.0256. Min Act: -0.0000

Data Index: 547206 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 2.5533. Min Range: -2.5533

Max Act: 2.0828. Min Act: -0.0000

Data Index: 207919 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 2.5533. Min Range: -2.5533

Max Act: 2.0432. Min Act: -0.0000

Data Index: 359123 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.8286. Min Act: -0.0000

Data Index: 656125 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.8187. Min Act: -0.0000

Data Index: 620686 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.8267. Min Act: -0.0000

Data Index: 846518 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.8976. Min Act: -0.0000

Data Index: 1330281 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.8625. Min Act: -0.0000

Data Index: 895416 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.7099. Min Act: -0.0000

Data Index: 897968 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.8149. Min Act: -0.0000

Data Index: 879037 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.8063. Min Act: -0.0000

Data Index: 411882 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.8700. Min Act: -0.0000

Data Index: 71157 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.5938. Min Act: -0.0000

Data Index: 407524 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.8764. Min Act: -0.0000

Data Index: 539719 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.7541. Min Act: -0.0000

Data Index: 578262 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.7642. Min Act: -0.0000

Data Index: 1274132 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.6997. Min Act: -0.0000

Data Index: 103347 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 2.5533. Min Range: -2.5533

Max Act: 1.7336. Min Act: -0.0000

Data Index: 687293 (C4 (Web Text))

Max Activating Token Index: 1022