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

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

Neuron 2248 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: 0.6638. Min Range: -0.6638

Max Act: 0.6638. Min Act: -0.0001

Data Index: 70636 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5957. Min Act: -0.0001

Data Index: 988837 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.6179. Min Act: -0.0001

Data Index: 1031166 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.6142. Min Act: -0.0001

Data Index: 1145960 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5526. Min Act: -0.0001

Data Index: 1567862 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5607. Min Act: -0.0001

Data Index: 573366 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.6006. Min Act: -0.0001

Data Index: 772568 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5089. Min Act: -0.0001

Data Index: 118055 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5141. Min Act: -0.0001

Data Index: 59478 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4912. Min Act: -0.0001

Data Index: 652761 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5174. Min Act: -0.0001

Data Index: 142629 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4317. Min Act: -0.0001

Data Index: 688461 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4485. Min Act: -0.0001

Data Index: 239537 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4821. Min Act: -0.0001

Data Index: 1332038 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4762. Min Act: -0.0001

Data Index: 1337363 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4730. Min Act: -0.0001

Data Index: 77355 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1004785 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4517. Min Act: -0.0001

Data Index: 617454 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4475. Min Act: -0.0001

Data Index: 1079151 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3986. Min Act: -0.0001

Data Index: 263041 (C4 (Web Text))

Max Activating Token Index: 804