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

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

Neuron 244 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: 4.6755. Min Range: -4.6755

Max Act: 4.6755. Min Act: -0.1700

Data Index: 1421026 (Python Code)

Max Activating Token Index: 554

Text #1

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.4634. Min Act: -0.1650

Data Index: 1464720 (Python Code)

Max Activating Token Index: 565

Text #2

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.3899. Min Act: -0.1700

Data Index: 1502473 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.3852. Min Act: -0.1650

Data Index: 1492293 (Python Code)

Max Activating Token Index: 453

Text #4

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.3714. Min Act: -0.1700

Data Index: 1508611 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.3253. Min Act: -0.1698

Data Index: 1527516 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.2603. Min Act: -0.1698

Data Index: 1576274 (Python Code)

Max Activating Token Index: 648

Text #7

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.2506. Min Act: -0.1700

Data Index: 1578810 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.2724. Min Act: -0.1699

Data Index: 1408811 (Python Code)

Max Activating Token Index: 704

Text #9

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.1916. Min Act: -0.1697

Data Index: 1379999 (Python Code)

Max Activating Token Index: 182

Text #10

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.1850. Min Act: -0.1694

Data Index: 1418355 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.1908. Min Act: -0.1695

Data Index: 1556332 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.2004. Min Act: -0.1700

Data Index: 1365887 (Python Code)

Max Activating Token Index: 798

Text #13

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.1595. Min Act: -0.1700

Data Index: 1439363 (Python Code)

Max Activating Token Index: 534

Text #14

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.1791. Min Act: -0.1700

Data Index: 1409231 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.1503. Min Act: -0.1699

Data Index: 1487434 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.1292. Min Act: -0.1684

Data Index: 1382997 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.1281. Min Act: -0.1700

Data Index: 1530191 (Python Code)

Max Activating Token Index: 899

Text #18

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.1544. Min Act: -0.1700

Data Index: 1456456 (Python Code)

Max Activating Token Index: 804

Text #19

Max Range: 4.6755. Min Range: -4.6755

Max Act: 4.0965. Min Act: -0.1700

Data Index: 1499084 (Python Code)

Max Activating Token Index: 112