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

Dataset: Open Web Text

Neuron 698 in Layer 0

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: 3.8443. Min Range: -3.8443

Max Act: 3.8443. Min Act: -0.1700

Data Index: 3081255 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.8144. Min Act: -0.1700

Data Index: 175084 (Open Web Text)

Max Activating Token Index: 819

Text #2

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.7901. Min Act: -0.1700

Data Index: 1467637 (Open Web Text)

Max Activating Token Index: 756

Text #3

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.7968. Min Act: -0.1700

Data Index: 6024258 (Open Web Text)

Max Activating Token Index: 967

Text #4

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.7591. Min Act: -0.1699

Data Index: 4025725 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.6691. Min Act: -0.1698

Data Index: 5506974 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.7916. Min Act: -0.1700

Data Index: 3825996 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.7490. Min Act: -0.1700

Data Index: 1622180 (Open Web Text)

Max Activating Token Index: 731

Text #8

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.6668. Min Act: -0.1700

Data Index: 2912310 (Open Web Text)

Max Activating Token Index: 851

Text #9

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.6779. Min Act: -0.1700

Data Index: 3362822 (Open Web Text)

Max Activating Token Index: 989

Text #10

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.6607. Min Act: -0.1700

Data Index: 3369689 (Open Web Text)

Max Activating Token Index: 1001

Text #11

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.6600. Min Act: -0.1700

Data Index: 6484019 (Open Web Text)

Max Activating Token Index: 963

Text #12

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.6722. Min Act: -0.1700

Data Index: 5453274 (Open Web Text)

Max Activating Token Index: 824

Text #13

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.6839. Min Act: -0.1699

Data Index: 6965812 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.6405. Min Act: -0.1700

Data Index: 3718540 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.6901. Min Act: -0.1700

Data Index: 8728805 (Open Web Text)

Max Activating Token Index: 1016

Text #16

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.7061. Min Act: -0.1700

Data Index: 2426910 (Open Web Text)

Max Activating Token Index: 405

Text #17

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.7121. Min Act: -0.1700

Data Index: 3131572 (Open Web Text)

Max Activating Token Index: 732

Text #18

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.7454. Min Act: -0.1700

Data Index: 2446703 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.8443. Min Range: -3.8443

Max Act: 3.7113. Min Act: -0.1700

Data Index: 3152059 (Open Web Text)

Max Activating Token Index: 1003