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

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

Neuron 3508 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3139. Min Range: -2.3139

Max Act: 2.3139. Min Act: -0.0000

Data Index: 1501319 (Python Code)

Max Activating Token Index: 43

Text #1

Max Range: 2.3139. Min Range: -2.3139

Max Act: 2.1230. Min Act: -0.0000

Data Index: 1457859 (Python Code)

Max Activating Token Index: 244

Text #2

Max Range: 2.3139. Min Range: -2.3139

Max Act: 2.0848. Min Act: -0.0000

Data Index: 1406576 (Python Code)

Max Activating Token Index: 949

Text #3

Max Range: 2.3139. Min Range: -2.3139

Max Act: 2.1288. Min Act: -0.0000

Data Index: 1402849 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.8828. Min Act: -0.0000

Data Index: 1505438 (Python Code)

Max Activating Token Index: 47

Text #5

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.9022. Min Act: -0.0000

Data Index: 1649626 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.9813. Min Act: -0.0000

Data Index: 1542411 (Python Code)

Max Activating Token Index: 92

Text #7

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.9373. Min Act: -0.0000

Data Index: 1576310 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.8841. Min Act: -0.0000

Data Index: 1377996 (Python Code)

Max Activating Token Index: 752

Text #9

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.8169. Min Act: -0.0000

Data Index: 1516492 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.7199. Min Act: -0.0000

Data Index: 1441704 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.7285. Min Act: -0.0000

Data Index: 1568108 (Python Code)

Max Activating Token Index: 374

Text #12

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1502588 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.6893. Min Act: -0.0000

Data Index: 1500051 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.6744. Min Act: -0.0001

Data Index: 1444335 (Python Code)

Max Activating Token Index: 99

Text #15

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.6733. Min Act: -0.0000

Data Index: 1522806 (Python Code)

Max Activating Token Index: 645

Text #16

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.6693. Min Act: -0.0000

Data Index: 1445098 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1569633 (Python Code)

Max Activating Token Index: 492

Text #18

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.5850. Min Act: -0.0001

Data Index: 1632371 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 2.3139. Min Range: -2.3139

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1446620 (Python Code)

Max Activating Token Index: 179