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

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

Neuron 1768 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: 4.5698. Min Range: -4.5698

Max Act: 4.5603. Min Act: -0.1700

Data Index: 318037 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 4.5698. Min Range: -4.5698

Max Act: 4.5698. Min Act: -0.1700

Data Index: 115334 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 4.5698. Min Range: -4.5698

Max Act: 4.3680. Min Act: -0.1699

Data Index: 768668 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 4.5698. Min Range: -4.5698

Max Act: 4.3498. Min Act: -0.1693

Data Index: 499549 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 4.5698. Min Range: -4.5698

Max Act: 4.2770. Min Act: -0.1700

Data Index: 355404 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 4.5698. Min Range: -4.5698

Max Act: 4.2060. Min Act: -0.1699

Data Index: 794420 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.5698. Min Range: -4.5698

Max Act: 4.1641. Min Act: -0.1700

Data Index: 371671 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 4.5698. Min Range: -4.5698

Max Act: 4.1063. Min Act: -0.1700

Data Index: 1383847 (Python Code)

Max Activating Token Index: 895

Text #8

Max Range: 4.5698. Min Range: -4.5698

Max Act: 4.0101. Min Act: -0.1700

Data Index: 1604300 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.9946. Min Act: -0.1700

Data Index: 708844 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.9644. Min Act: -0.1699

Data Index: 1295880 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.9671. Min Act: -0.1699

Data Index: 1450047 (Python Code)

Max Activating Token Index: 734

Text #12

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.8994. Min Act: -0.1700

Data Index: 841727 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.9071. Min Act: -0.1700

Data Index: 1457699 (Python Code)

Max Activating Token Index: 570

Text #14

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.8850. Min Act: -0.1700

Data Index: 1620786 (Python Code)

Max Activating Token Index: 896

Text #15

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.8869. Min Act: -0.1700

Data Index: 1386866 (Python Code)

Max Activating Token Index: 336

Text #16

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.8781. Min Act: -0.1700

Data Index: 1634183 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.8673. Min Act: -0.1700

Data Index: 1135587 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.8994. Min Act: -0.1700

Data Index: 1012665 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 4.5698. Min Range: -4.5698

Max Act: 3.8267. Min Act: -0.1699

Data Index: 522408 (C4 (Web Text))

Max Activating Token Index: 653