Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 52 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.2187. Min Act: -0.1700

Data Index: 1354525 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.2187. Min Act: -0.1700

Data Index: 972612 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.1715. Min Act: -0.1700

Data Index: 843010 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.1715. Min Act: -0.1700

Data Index: 425821 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.1400. Min Act: -0.1700

Data Index: 1227145 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.1558. Min Act: -0.1700

Data Index: 1042432 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.1400. Min Act: -0.1700

Data Index: 1288078 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.1085. Min Act: -0.1700

Data Index: 1218982 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0927. Min Act: -0.1700

Data Index: 34574 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.1085. Min Act: -0.1700

Data Index: 535770 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0927. Min Act: -0.1700

Data Index: 925605 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0927. Min Act: -0.1700

Data Index: 15132 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0769. Min Act: -0.1700

Data Index: 1315095 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0769. Min Act: -0.1700

Data Index: 894880 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0769. Min Act: -0.1700

Data Index: 659907 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0612. Min Act: -0.1700

Data Index: 1234373 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0612. Min Act: -0.1700

Data Index: 897696 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0454. Min Act: -0.1700

Data Index: 969949 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0296. Min Act: -0.1700

Data Index: 157901 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.2187. Min Range: -3.2187

Max Act: 3.0454. Min Act: -0.1700

Data Index: 731778 (C4 (Web Text))

Max Activating Token Index: 683