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

Dataset: Open Web Text

Neuron 1714 in Layer 4

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: 4.0850. Min Range: -4.0850

Max Act: 4.0850. Min Act: -0.1700

Data Index: 3515590 (Open Web Text)

Max Activating Token Index: 925

Text #1

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0308. Min Act: -0.1700

Data Index: 4645427 (Open Web Text)

Max Activating Token Index: 917

Text #2

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0148. Min Act: -0.1700

Data Index: 8066709 (Open Web Text)

Max Activating Token Index: 694

Text #3

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0100. Min Act: -0.1700

Data Index: 813821 (Open Web Text)

Max Activating Token Index: 592

Text #4

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9840. Min Act: -0.1700

Data Index: 7792104 (Open Web Text)

Max Activating Token Index: 956

Text #5

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9950. Min Act: -0.1700

Data Index: 4538705 (Open Web Text)

Max Activating Token Index: 952

Text #6

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0109. Min Act: -0.1700

Data Index: 4150174 (Open Web Text)

Max Activating Token Index: 986

Text #7

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9714. Min Act: -0.1700

Data Index: 594116 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9812. Min Act: -0.1700

Data Index: 3016561 (Open Web Text)

Max Activating Token Index: 712

Text #9

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0236. Min Act: -0.1700

Data Index: 5888915 (Open Web Text)

Max Activating Token Index: 849

Text #10

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9594. Min Act: -0.1700

Data Index: 2228163 (Open Web Text)

Max Activating Token Index: 657

Text #11

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9432. Min Act: -0.1700

Data Index: 3084202 (Open Web Text)

Max Activating Token Index: 543

Text #12

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9647. Min Act: -0.1700

Data Index: 5805408 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9482. Min Act: -0.1700

Data Index: 595813 (Open Web Text)

Max Activating Token Index: 971

Text #14

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9595. Min Act: -0.1700

Data Index: 2493454 (Open Web Text)

Max Activating Token Index: 620

Text #15

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9452. Min Act: -0.1700

Data Index: 475932 (Open Web Text)

Max Activating Token Index: 867

Text #16

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9196. Min Act: -0.1700

Data Index: 5585775 (Open Web Text)

Max Activating Token Index: 848

Text #17

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9297. Min Act: -0.1700

Data Index: 4698045 (Open Web Text)

Max Activating Token Index: 837

Text #18

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.8968. Min Act: -0.1700

Data Index: 7659809 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9067. Min Act: -0.1700

Data Index: 4336121 (Open Web Text)

Max Activating Token Index: 978