Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4876 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.8752. Min Act: -0.0001

Data Index: 930229 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.7822. Min Act: -0.0001

Data Index: 30206 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.7202. Min Act: -0.0000

Data Index: 901523 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.6520. Min Act: -0.0001

Data Index: 67382 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.5488. Min Act: -0.0001

Data Index: 127656 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.5009. Min Act: -0.0000

Data Index: 992094 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.7137. Min Act: -0.0000

Data Index: 1176597 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.4799. Min Act: -0.0000

Data Index: 784967 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.2685. Min Act: -0.0000

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.4525. Min Act: -0.0001

Data Index: 968938 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.4919. Min Act: -0.0000

Data Index: 980097 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.4067. Min Act: -0.0000

Data Index: 864484 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.3913. Min Act: -0.0001

Data Index: 1093725 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.3285. Min Act: -0.0001

Data Index: 339544 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.3111. Min Act: -0.0000

Data Index: 215072 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.2712. Min Act: -0.0000

Data Index: 88176 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.0513. Min Act: -0.0001

Data Index: 242090 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.1692. Min Act: -0.0000

Data Index: 36229 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.1613. Min Act: -0.0000

Data Index: 1135272 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 2.8752. Min Range: -2.8752

Max Act: 2.2889. Min Act: -0.0000

Data Index: 792476 (C4 (Web Text))

Max Activating Token Index: 280