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

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

Neuron 913 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.7932. Min Act: -0.1700

Data Index: 666054 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.7932. Min Act: -0.1700

Data Index: 277708 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.6993. Min Act: -0.1700

Data Index: 583082 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.6680. Min Act: -0.1700

Data Index: 955629 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.6524. Min Act: -0.1700

Data Index: 927793 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.6524. Min Act: -0.1700

Data Index: 84480 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.6054. Min Act: -0.1700

Data Index: 224475 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.6054. Min Act: -0.1700

Data Index: 717223 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5741. Min Act: -0.1700

Data Index: 415733 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5428. Min Act: -0.1700

Data Index: 697550 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5428. Min Act: -0.1700

Data Index: 218504 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5428. Min Act: -0.1700

Data Index: 693822 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5428. Min Act: -0.1700

Data Index: 765888 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5428. Min Act: -0.1700

Data Index: 201409 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1124854 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5271. Min Act: -0.1700

Data Index: 204452 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5114. Min Act: -0.1700

Data Index: 678119 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.5114. Min Act: -0.1700

Data Index: 904589 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.4801. Min Act: -0.1700

Data Index: 828495 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 3.7932. Min Range: -3.7932

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1156688 (C4 (Web Text))

Max Activating Token Index: 843