Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1558 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.3233. Min Act: -0.1700

Data Index: 1250575 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.2375. Min Act: -0.1700

Data Index: 5280889 (Open Web Text)

Max Activating Token Index: 908

Text #2

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.2592. Min Act: -0.1700

Data Index: 6999834 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.2393. Min Act: -0.1700

Data Index: 1801539 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.1681. Min Act: -0.1700

Data Index: 3259176 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.1804. Min Act: -0.1700

Data Index: 7619284 (Open Web Text)

Max Activating Token Index: 764

Text #6

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.2020. Min Act: -0.1700

Data Index: 824587 (Open Web Text)

Max Activating Token Index: 89

Text #7

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.1951. Min Act: -0.1700

Data Index: 7610852 (Open Web Text)

Max Activating Token Index: 207

Text #8

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.1585. Min Act: -0.1700

Data Index: 1016457 (Open Web Text)

Max Activating Token Index: 622

Text #9

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.1158. Min Act: -0.1700

Data Index: 3343118 (Open Web Text)

Max Activating Token Index: 838

Text #10

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.1135. Min Act: -0.1700

Data Index: 189783 (Open Web Text)

Max Activating Token Index: 193

Text #11

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.0721. Min Act: -0.1700

Data Index: 1112679 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.0308. Min Act: -0.1700

Data Index: 2113044 (Open Web Text)

Max Activating Token Index: 1009

Text #13

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.0601. Min Act: -0.1700

Data Index: 7364618 (Open Web Text)

Max Activating Token Index: 662

Text #14

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.0438. Min Act: -0.1700

Data Index: 4243457 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 6.3233. Min Range: -6.3233

Max Act: 5.9693. Min Act: -0.1700

Data Index: 8788903 (Open Web Text)

Max Activating Token Index: 709

Text #16

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.0571. Min Act: -0.1700

Data Index: 7610851 (Open Web Text)

Max Activating Token Index: 925

Text #17

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.0101. Min Act: -0.1700

Data Index: 175271 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 6.3233. Min Range: -6.3233

Max Act: 5.9635. Min Act: -0.1700

Data Index: 6478787 (Open Web Text)

Max Activating Token Index: 801

Text #19

Max Range: 6.3233. Min Range: -6.3233

Max Act: 6.0193. Min Act: -0.1700

Data Index: 8571815 (Open Web Text)

Max Activating Token Index: 641