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

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

Neuron 770 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: 3.1846. Min Range: -3.1846

Max Act: 3.1846. Min Act: -0.1700

Data Index: 1511754 (Python Code)

Max Activating Token Index: 904

Text #1

Max Range: 3.1846. Min Range: -3.1846

Max Act: 3.1076. Min Act: -0.1616

Data Index: 1424492 (Python Code)

Max Activating Token Index: 858

Text #2

Max Range: 3.1846. Min Range: -3.1846

Max Act: 3.1055. Min Act: -0.1699

Data Index: 1648161 (Python Code)

Max Activating Token Index: 312

Text #3

Max Range: 3.1846. Min Range: -3.1846

Max Act: 3.0807. Min Act: -0.1699

Data Index: 1545906 (Python Code)

Max Activating Token Index: 877

Text #4

Max Range: 3.1846. Min Range: -3.1846

Max Act: 3.0007. Min Act: -0.1700

Data Index: 88078 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.9875. Min Act: -0.1699

Data Index: 1514793 (Python Code)

Max Activating Token Index: 428

Text #6

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.9752. Min Act: -0.1700

Data Index: 1370152 (Python Code)

Max Activating Token Index: 880

Text #7

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.9590. Min Act: -0.1665

Data Index: 1378052 (Python Code)

Max Activating Token Index: 963

Text #8

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.9380. Min Act: -0.1699

Data Index: 1648603 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.9262. Min Act: -0.1700

Data Index: 1512859 (Python Code)

Max Activating Token Index: 403

Text #10

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.9044. Min Act: -0.1699

Data Index: 1392934 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.8894. Min Act: -0.1699

Data Index: 1450111 (Python Code)

Max Activating Token Index: 854

Text #12

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.8982. Min Act: -0.1700

Data Index: 1629514 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.8755. Min Act: -0.1700

Data Index: 1478812 (Python Code)

Max Activating Token Index: 574

Text #14

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.8678. Min Act: -0.1698

Data Index: 1474198 (Python Code)

Max Activating Token Index: 437

Text #15

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.8493. Min Act: -0.1700

Data Index: 1535885 (Python Code)

Max Activating Token Index: 999

Text #16

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.8644. Min Act: -0.1700

Data Index: 103598 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.8399. Min Act: -0.1698

Data Index: 1615852 (Python Code)

Max Activating Token Index: 612

Text #18

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.8339. Min Act: -0.1678

Data Index: 1620207 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 3.1846. Min Range: -3.1846

Max Act: 2.8382. Min Act: -0.1699

Data Index: 1405738 (Python Code)

Max Activating Token Index: 276