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

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

Neuron 1046 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: 6.2724. Min Range: -6.2724

Max Act: 6.2724. Min Act: -0.0000

Data Index: 880960 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 6.2724. Min Range: -6.2724

Max Act: 6.0122. Min Act: -0.0000

Data Index: 1010472 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.8002. Min Act: -0.0001

Data Index: 681810 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.8314. Min Act: -0.0001

Data Index: 227159 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.3935. Min Act: -0.0000

Data Index: 669945 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.4115. Min Act: -0.0001

Data Index: 1204272 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.2838. Min Act: -0.0001

Data Index: 1306761 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.3685. Min Act: -0.0001

Data Index: 1336266 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.2029. Min Act: -0.0000

Data Index: 121346 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.2110. Min Act: -0.0000

Data Index: 18493 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.1982. Min Act: -0.0000

Data Index: 204647 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.1748. Min Act: -0.0000

Data Index: 825618 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.1650. Min Act: -0.0000

Data Index: 490577 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 6.2724. Min Range: -6.2724

Max Act: 4.9440. Min Act: -0.0000

Data Index: 1268672 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.1184. Min Act: -0.0000

Data Index: 1068887 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.2768. Min Act: -0.0000

Data Index: 1089506 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.1176. Min Act: -0.0000

Data Index: 215774 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.0379. Min Act: -0.0001

Data Index: 1332275 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 6.2724. Min Range: -6.2724

Max Act: 4.9978. Min Act: -0.0000

Data Index: 501737 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 6.2724. Min Range: -6.2724

Max Act: 4.7632. Min Act: -0.0000

Data Index: 753785 (C4 (Web Text))

Max Activating Token Index: 186