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

Dataset: Open Web Text

Neuron 1526 in Layer 2

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: 4.1667. Min Range: -4.1667

Max Act: 4.1667. Min Act: -0.1700

Data Index: 1178015 (Open Web Text)

Max Activating Token Index: 313

Text #1

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0993. Min Act: -0.1700

Data Index: 2967917 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0575. Min Act: -0.1700

Data Index: 8006256 (Open Web Text)

Max Activating Token Index: 94

Text #3

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.9497. Min Act: -0.1700

Data Index: 5741010 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.9712. Min Act: -0.1700

Data Index: 1828322 (Open Web Text)

Max Activating Token Index: 796

Text #5

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.9282. Min Act: -0.1700

Data Index: 677752 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.9251. Min Act: -0.1700

Data Index: 8736698 (Open Web Text)

Max Activating Token Index: 127

Text #7

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.9369. Min Act: -0.1700

Data Index: 1201912 (Open Web Text)

Max Activating Token Index: 934

Text #8

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.9058. Min Act: -0.1700

Data Index: 4872645 (Open Web Text)

Max Activating Token Index: 719

Text #9

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8795. Min Act: -0.1700

Data Index: 2310578 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8673. Min Act: -0.1700

Data Index: 1756593 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8670. Min Act: -0.1700

Data Index: 1963481 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8244. Min Act: -0.1700

Data Index: 5041775 (Open Web Text)

Max Activating Token Index: 410

Text #13

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8286. Min Act: -0.1700

Data Index: 193166 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8436. Min Act: -0.1700

Data Index: 6281435 (Open Web Text)

Max Activating Token Index: 552

Text #15

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8162. Min Act: -0.1700

Data Index: 5676883 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8091. Min Act: -0.1700

Data Index: 1866016 (Open Web Text)

Max Activating Token Index: 737

Text #17

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.7825. Min Act: -0.1700

Data Index: 1844175 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.7889. Min Act: -0.1700

Data Index: 2972106 (Open Web Text)

Max Activating Token Index: 211

Text #19

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.7760. Min Act: -0.1700

Data Index: 4563834 (Open Web Text)

Max Activating Token Index: 315