Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1872 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.1521. Min Act: -0.1700

Data Index: 358557 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.1521. Min Act: -0.1700

Data Index: 349188 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.1363. Min Act: -0.1700

Data Index: 166070 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.1206. Min Act: -0.1700

Data Index: 62372 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0733. Min Act: -0.1700

Data Index: 93928 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.1048. Min Act: -0.1700

Data Index: 307769 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0575. Min Act: -0.1700

Data Index: 399579 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.1206. Min Act: -0.1700

Data Index: 453121 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0733. Min Act: -0.1700

Data Index: 541375 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0890. Min Act: -0.1700

Data Index: 670890 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0890. Min Act: -0.1700

Data Index: 637493 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0575. Min Act: -0.1700

Data Index: 557368 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0733. Min Act: -0.1700

Data Index: 1350783 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0417. Min Act: -0.1700

Data Index: 35832 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0259. Min Act: -0.1700

Data Index: 266682 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0733. Min Act: -0.1700

Data Index: 1348340 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0259. Min Act: -0.1700

Data Index: 336405 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0101. Min Act: -0.1700

Data Index: 22996 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0575. Min Act: -0.1700

Data Index: 1339931 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 3.1521. Min Range: -3.1521

Max Act: 3.0575. Min Act: -0.1700

Data Index: 421456 (C4 (Web Text))

Max Activating Token Index: 673