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

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

Neuron 1487 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: 3.1874. Min Range: -3.1874

Max Act: 3.1874. Min Act: -0.1697

Data Index: 1598929 (Python Code)

Max Activating Token Index: 351

Text #1

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.9707. Min Act: -0.1699

Data Index: 1612215 (Python Code)

Max Activating Token Index: 663

Text #2

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.9664. Min Act: -0.1700

Data Index: 1640442 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.9497. Min Act: -0.1698

Data Index: 1597691 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.9146. Min Act: -0.1692

Data Index: 1435770 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.9156. Min Act: -0.1700

Data Index: 1474627 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.9273. Min Act: -0.0444

Data Index: 1652420 (Python Code)

Max Activating Token Index: 138

Text #7

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8884. Min Act: -0.1700

Data Index: 1483091 (Python Code)

Max Activating Token Index: 97

Text #8

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8864. Min Act: -0.1700

Data Index: 1457378 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8622. Min Act: -0.1649

Data Index: 1418618 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8446. Min Act: -0.1699

Data Index: 1631424 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8590. Min Act: -0.1700

Data Index: 1495925 (Python Code)

Max Activating Token Index: 661

Text #12

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8366. Min Act: -0.1699

Data Index: 1044538 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8285. Min Act: -0.1700

Data Index: 1494884 (Python Code)

Max Activating Token Index: 784

Text #14

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8198. Min Act: -0.1699

Data Index: 1444499 (Python Code)

Max Activating Token Index: 799

Text #15

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8137. Min Act: -0.1700

Data Index: 1405235 (Python Code)

Max Activating Token Index: 599

Text #16

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8249. Min Act: -0.1698

Data Index: 1487449 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.8219. Min Act: -0.1700

Data Index: 367313 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.7857. Min Act: -0.1699

Data Index: 96080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.7823. Min Act: -0.1696

Data Index: 1448973 (Python Code)

Max Activating Token Index: 961