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

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

Neuron 827 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: 4.8467. Min Range: -4.8467

Max Act: 4.8467. Min Act: -0.1700

Data Index: 1112724 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.5375. Min Act: -0.1700

Data Index: 1192860 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.5119. Min Act: -0.1700

Data Index: 1206908 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.4414. Min Act: -0.1700

Data Index: 899493 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.4484. Min Act: -0.1700

Data Index: 1600861 (Python Code)

Max Activating Token Index: 903

Text #5

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.4160. Min Act: -0.1700

Data Index: 935795 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3996. Min Act: -0.1700

Data Index: 1153965 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.4118. Min Act: -0.1700

Data Index: 1137411 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.4013. Min Act: -0.1700

Data Index: 819903 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.4106. Min Act: -0.1700

Data Index: 1184006 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3986. Min Act: -0.1700

Data Index: 1008940 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3491. Min Act: -0.1700

Data Index: 126051 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3769. Min Act: -0.1700

Data Index: 215921 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3271. Min Act: -0.1700

Data Index: 734119 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3307. Min Act: -0.1700

Data Index: 293303 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3082. Min Act: -0.1700

Data Index: 491539 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.2796. Min Act: -0.1700

Data Index: 1191554 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3058. Min Act: -0.1700

Data Index: 394317 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3047. Min Act: -0.1700

Data Index: 602129 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3030. Min Act: -0.1700

Data Index: 1082511 (C4 (Web Text))

Max Activating Token Index: 96