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

Dataset: Open Web Text

Neuron 333 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.3737. Min Act: -0.1700

Data Index: 3139609 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.3424. Min Act: -0.1700

Data Index: 7649559 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.3112. Min Act: -0.1700

Data Index: 6250629 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2799. Min Act: -0.1700

Data Index: 2967301 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2799. Min Act: -0.1700

Data Index: 3734835 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2799. Min Act: -0.1700

Data Index: 5769583 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2487. Min Act: -0.1700

Data Index: 8658826 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2487. Min Act: -0.1700

Data Index: 6510859 (Open Web Text)

Max Activating Token Index: 126

Text #8

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2487. Min Act: -0.1700

Data Index: 4537378 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2487. Min Act: -0.1700

Data Index: 1498382 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2487. Min Act: -0.1700

Data Index: 5770894 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2174. Min Act: -0.1700

Data Index: 2192539 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2174. Min Act: -0.1700

Data Index: 1110616 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2174. Min Act: -0.1700

Data Index: 5773750 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2174. Min Act: -0.1700

Data Index: 1496087 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2174. Min Act: -0.1700

Data Index: 4890027 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2174. Min Act: -0.1700

Data Index: 4812839 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2174. Min Act: -0.1700

Data Index: 1817146 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2174. Min Act: -0.1700

Data Index: 69759 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 5.3737. Min Range: -5.3737

Max Act: 5.2174. Min Act: -0.1700

Data Index: 4037266 (Open Web Text)

Max Activating Token Index: 2