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

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

Neuron 321 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: 3.2178. Min Range: -3.2178

Max Act: 3.2178. Min Act: -0.1700

Data Index: 272040 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.2178. Min Act: -0.1700

Data Index: 481398 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.2178. Min Act: -0.1700

Data Index: 335225 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.1706. Min Act: -0.1700

Data Index: 627484 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.1234. Min Act: -0.1700

Data Index: 460057 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0918. Min Act: -0.1700

Data Index: 1219213 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.1076. Min Act: -0.1700

Data Index: 854326 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.1076. Min Act: -0.1700

Data Index: 179861 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0918. Min Act: -0.1700

Data Index: 936192 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0761. Min Act: -0.1700

Data Index: 654538 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0761. Min Act: -0.1700

Data Index: 501783 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0287. Min Act: -0.1700

Data Index: 259979 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0445. Min Act: -0.1700

Data Index: 1093250 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0445. Min Act: -0.1700

Data Index: 487952 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0287. Min Act: -0.1700

Data Index: 1159865 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0287. Min Act: -0.1700

Data Index: 696708 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 3.2178. Min Range: -3.2178

Max Act: 2.9971. Min Act: -0.1700

Data Index: 755450 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 3.2178. Min Range: -3.2178

Max Act: 3.0129. Min Act: -0.1700

Data Index: 371051 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 3.2178. Min Range: -3.2178

Max Act: 2.9971. Min Act: -0.1700

Data Index: 697497 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 3.2178. Min Range: -3.2178

Max Act: 2.9813. Min Act: -0.1700

Data Index: 865667 (C4 (Web Text))

Max Activating Token Index: 578