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

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

Neuron 3381 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: 1.0766. Min Range: -1.0766

Max Act: 0.9839. Min Act: -0.0001

Data Index: 10241 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 1.0766. Min Range: -1.0766

Max Act: 1.0766. Min Act: -0.0001

Data Index: 999087 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9762. Min Act: -0.0001

Data Index: 637139 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9550. Min Act: -0.0001

Data Index: 1347692 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9790. Min Act: -0.0001

Data Index: 740946 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8801. Min Act: -0.0001

Data Index: 634562 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9277. Min Act: -0.0001

Data Index: 1264037 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9551. Min Act: -0.0001

Data Index: 722757 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8849. Min Act: -0.0001

Data Index: 559790 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8455. Min Act: -0.0001

Data Index: 620204 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9053. Min Act: -0.0001

Data Index: 757934 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9286. Min Act: -0.0001

Data Index: 433581 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9197. Min Act: -0.0001

Data Index: 644618 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8949. Min Act: -0.0001

Data Index: 510787 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9749. Min Act: -0.0001

Data Index: 1079131 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.0766. Min Range: -1.0766

Max Act: 1.0115. Min Act: -0.0001

Data Index: 881627 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8755. Min Act: -0.0001

Data Index: 181062 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8895. Min Act: -0.0001

Data Index: 623067 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9049. Min Act: -0.0001

Data Index: 163497 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8621. Min Act: -0.0001

Data Index: 1043714 (C4 (Web Text))

Max Activating Token Index: 645