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

Dataset: Open Web Text

Neuron 51 in Layer 5

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: 3.8120. Min Range: -3.8120

Max Act: 3.7807. Min Act: -0.1700

Data Index: 4080683 (Open Web Text)

Max Activating Token Index: 1019

Text #1

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.8120. Min Act: -0.1700

Data Index: 1764070 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.8067. Min Act: -0.1700

Data Index: 7853878 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.8111. Min Act: -0.1700

Data Index: 5883081 (Open Web Text)

Max Activating Token Index: 150

Text #4

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.7730. Min Act: -0.1700

Data Index: 6607139 (Open Web Text)

Max Activating Token Index: 731

Text #5

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.7712. Min Act: -0.1700

Data Index: 5653803 (Open Web Text)

Max Activating Token Index: 748

Text #6

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.7399. Min Act: -0.1700

Data Index: 349945 (Open Web Text)

Max Activating Token Index: 932

Text #7

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6980. Min Act: -0.1700

Data Index: 17873 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.7155. Min Act: -0.1700

Data Index: 6656350 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6570. Min Act: -0.1700

Data Index: 1083349 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6874. Min Act: -0.1700

Data Index: 1344296 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6861. Min Act: -0.1700

Data Index: 6100327 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6684. Min Act: -0.1700

Data Index: 548508 (Open Web Text)

Max Activating Token Index: 1011

Text #13

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6850. Min Act: -0.1700

Data Index: 1081872 (Open Web Text)

Max Activating Token Index: 39

Text #14

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6600. Min Act: -0.1700

Data Index: 4778159 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6675. Min Act: -0.1700

Data Index: 8663314 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6593. Min Act: -0.1700

Data Index: 6129502 (Open Web Text)

Max Activating Token Index: 577

Text #17

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6585. Min Act: -0.1700

Data Index: 1529055 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6467. Min Act: -0.1700

Data Index: 1483843 (Open Web Text)

Max Activating Token Index: 637

Text #19

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6580. Min Act: -0.1700

Data Index: 463669 (Open Web Text)

Max Activating Token Index: 864