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

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

Neuron 3675 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.7851. Min Act: -0.0000

Data Index: 37488 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.7445. Min Act: -0.0000

Data Index: 773623 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.6055. Min Act: -0.0000

Data Index: 744561 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.4353. Min Act: -0.0000

Data Index: 798114 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.4099. Min Act: -0.0000

Data Index: 870351 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.4137. Min Act: -0.0000

Data Index: 1199790 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.2473. Min Act: -0.0000

Data Index: 1096561 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.3646. Min Act: -0.0000

Data Index: 430808 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.2174. Min Act: -0.0000

Data Index: 35899 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.2481. Min Act: -0.0000

Data Index: 25581 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 2.7851. Min Range: -2.7851

Max Act: 1.9782. Min Act: -0.0000

Data Index: 376758 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.1778. Min Act: -0.0000

Data Index: 1240817 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.2512. Min Act: -0.0000

Data Index: 1240922 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.2304. Min Act: -0.0000

Data Index: 1178271 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.2175. Min Act: -0.0000

Data Index: 1178902 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.4669. Min Act: -0.0000

Data Index: 183005 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.1042. Min Act: -0.0000

Data Index: 166389 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.3367. Min Act: -0.0000

Data Index: 1034917 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 2.7851. Min Range: -2.7851

Max Act: 2.0937. Min Act: -0.0000

Data Index: 366969 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 2.7851. Min Range: -2.7851

Max Act: 1.7580. Min Act: -0.0000

Data Index: 83746 (C4 (Web Text))

Max Activating Token Index: 198