Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 1955 in Layer 40

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.2555. Min Act: -0.1700

Data Index: 753961 (Open Web Text)

Max Activating Token Index: 745

Text #1

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.1305. Min Act: -0.1700

Data Index: 5120097 (Open Web Text)

Max Activating Token Index: 123

Text #2

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.1305. Min Act: -0.1700

Data Index: 6914530 (Open Web Text)

Max Activating Token Index: 200

Text #3

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.1305. Min Act: -0.1700

Data Index: 525768 (Open Web Text)

Max Activating Token Index: 248

Text #4

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.0680. Min Act: -0.1700

Data Index: 6642303 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.0992. Min Act: -0.1700

Data Index: 3865822 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.0992. Min Act: -0.1700

Data Index: 1526726 (Open Web Text)

Max Activating Token Index: 150

Text #7

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.0680. Min Act: -0.1700

Data Index: 406781 (Open Web Text)

Max Activating Token Index: 732

Text #8

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.0680. Min Act: -0.1700

Data Index: 4278762 (Open Web Text)

Max Activating Token Index: 158

Text #9

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.0680. Min Act: -0.1700

Data Index: 958605 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.0367. Min Act: -0.1700

Data Index: 5689166 (Open Web Text)

Max Activating Token Index: 294

Text #11

Max Range: 7.2555. Min Range: -7.2555

Max Act: 7.0367. Min Act: -0.1700

Data Index: 8504873 (Open Web Text)

Max Activating Token Index: 87

Text #12

Max Range: 7.2555. Min Range: -7.2555

Max Act: 6.9742. Min Act: -0.1700

Data Index: 4218253 (Open Web Text)

Max Activating Token Index: 908

Text #13

Max Range: 7.2555. Min Range: -7.2555

Max Act: 6.9742. Min Act: -0.1700

Data Index: 7884009 (Open Web Text)

Max Activating Token Index: 895

Text #14

Max Range: 7.2555. Min Range: -7.2555

Max Act: 6.9430. Min Act: -0.1700

Data Index: 2270910 (Open Web Text)

Max Activating Token Index: 125

Text #15

Max Range: 7.2555. Min Range: -7.2555

Max Act: 6.9430. Min Act: -0.1700

Data Index: 3647270 (Open Web Text)

Max Activating Token Index: 892

Text #16

Max Range: 7.2555. Min Range: -7.2555

Max Act: 6.8805. Min Act: -0.1700

Data Index: 4076184 (Open Web Text)

Max Activating Token Index: 275

Text #17

Max Range: 7.2555. Min Range: -7.2555

Max Act: 6.8805. Min Act: -0.1700

Data Index: 6238766 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 7.2555. Min Range: -7.2555

Max Act: 6.8492. Min Act: -0.1700

Data Index: 3495866 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 7.2555. Min Range: -7.2555

Max Act: 6.8492. Min Act: -0.1700

Data Index: 5205657 (Open Web Text)

Max Activating Token Index: 680