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

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

Neuron 1433 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: 4.1790. Min Range: -4.1790

Max Act: 4.1790. Min Act: -0.1699

Data Index: 853258 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 4.1790. Min Range: -4.1790

Max Act: 4.0847. Min Act: -0.1697

Data Index: 65824 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 4.1790. Min Range: -4.1790

Max Act: 4.0460. Min Act: -0.1697

Data Index: 709347 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 4.1790. Min Range: -4.1790

Max Act: 4.0203. Min Act: -0.1697

Data Index: 729865 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.9735. Min Act: -0.1677

Data Index: 1479321 (Python Code)

Max Activating Token Index: 630

Text #5

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.9259. Min Act: -0.1699

Data Index: 1211809 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.9250. Min Act: -0.1700

Data Index: 334517 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.9517. Min Act: -0.1700

Data Index: 1272055 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8731. Min Act: -0.1699

Data Index: 440075 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.9094. Min Act: -0.1700

Data Index: 1005028 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8870. Min Act: -0.1700

Data Index: 217588 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8699. Min Act: -0.1664

Data Index: 1450308 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8658. Min Act: -0.1700

Data Index: 1381523 (Python Code)

Max Activating Token Index: 328

Text #13

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8688. Min Act: -0.1700

Data Index: 403785 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8630. Min Act: -0.1698

Data Index: 19745 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8782. Min Act: -0.1700

Data Index: 159770 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8789. Min Act: -0.1700

Data Index: 1208192 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8666. Min Act: -0.1700

Data Index: 221768 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8456. Min Act: -0.1700

Data Index: 1275548 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 4.1790. Min Range: -4.1790

Max Act: 3.8313. Min Act: -0.1700

Data Index: 387192 (C4 (Web Text))

Max Activating Token Index: 954