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

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

Neuron 491 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: 5.4899. Min Range: -5.4899

Max Act: 5.4899. Min Act: -0.1697

Data Index: 758959 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.4092. Min Act: -0.1690

Data Index: 871820 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.3249. Min Act: -0.1700

Data Index: 112867 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.2491. Min Act: -0.1681

Data Index: 649573 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.2254. Min Act: -0.1658

Data Index: 576143 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.2292. Min Act: -0.1699

Data Index: 1625885 (Python Code)

Max Activating Token Index: 946

Text #6

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.1871. Min Act: -0.1700

Data Index: 1214879 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.2017. Min Act: -0.1700

Data Index: 747240 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.1908. Min Act: -0.1698

Data Index: 1048405 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.1715. Min Act: -0.1700

Data Index: 1182844 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0978. Min Act: -0.1698

Data Index: 473018 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0699. Min Act: -0.1700

Data Index: 65951 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0836. Min Act: -0.1690

Data Index: 977716 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0911. Min Act: -0.1697

Data Index: 432279 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0416. Min Act: -0.1695

Data Index: 1258754 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0466. Min Act: -0.1699

Data Index: 385339 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0407. Min Act: -0.1698

Data Index: 623044 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0557. Min Act: -0.1698

Data Index: 1315721 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0348. Min Act: -0.1700

Data Index: 730148 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 5.4899. Min Range: -5.4899

Max Act: 5.0092. Min Act: -0.1695

Data Index: 747250 (C4 (Web Text))

Max Activating Token Index: 554