Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 992 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.7851. Min Act: -0.1700

Data Index: 682760 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.7448. Min Act: -0.1700

Data Index: 1571766 (Python Code)

Max Activating Token Index: 612

Text #2

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.6726. Min Act: -0.1700

Data Index: 1519269 (Python Code)

Max Activating Token Index: 117

Text #3

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.6012. Min Act: -0.1700

Data Index: 1437031 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5656. Min Act: -0.1700

Data Index: 1296981 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5702. Min Act: -0.1700

Data Index: 1611048 (Python Code)

Max Activating Token Index: 795

Text #6

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5686. Min Act: -0.1700

Data Index: 1587935 (Python Code)

Max Activating Token Index: 80

Text #7

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5360. Min Act: -0.1700

Data Index: 1578578 (Python Code)

Max Activating Token Index: 67

Text #8

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5089. Min Act: -0.1700

Data Index: 1509603 (Python Code)

Max Activating Token Index: 907

Text #9

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5116. Min Act: -0.1700

Data Index: 1595139 (Python Code)

Max Activating Token Index: 814

Text #10

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5006. Min Act: -0.1700

Data Index: 1536692 (Python Code)

Max Activating Token Index: 850

Text #11

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5338. Min Act: -0.1700

Data Index: 584074 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5102. Min Act: -0.1700

Data Index: 1633208 (Python Code)

Max Activating Token Index: 139

Text #13

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5111. Min Act: -0.1700

Data Index: 1637574 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.5116. Min Act: -0.1700

Data Index: 1641007 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.4957. Min Act: -0.1700

Data Index: 765977 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.4909. Min Act: -0.1700

Data Index: 137146 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.4756. Min Act: -0.1700

Data Index: 1417376 (Python Code)

Max Activating Token Index: 743

Text #18

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.4686. Min Act: -0.1700

Data Index: 1606195 (Python Code)

Max Activating Token Index: 775

Text #19

Max Range: 3.7851. Min Range: -3.7851

Max Act: 3.4866. Min Act: -0.1700

Data Index: 1412540 (Python Code)

Max Activating Token Index: 327