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

Dataset: Open Web Text

Neuron 945 in Layer 3

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: 3.0078. Min Range: -3.0078

Max Act: 3.0078. Min Act: -0.1700

Data Index: 5763347 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9723. Min Act: -0.1700

Data Index: 5763356 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9344. Min Act: -0.1700

Data Index: 5763372 (Open Web Text)

Max Activating Token Index: 910

Text #3

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8916. Min Act: -0.1700

Data Index: 5763374 (Open Web Text)

Max Activating Token Index: 923

Text #4

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8989. Min Act: -0.1700

Data Index: 5763360 (Open Web Text)

Max Activating Token Index: 762

Text #5

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8814. Min Act: -0.1700

Data Index: 5763368 (Open Web Text)

Max Activating Token Index: 785

Text #6

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8538. Min Act: -0.1700

Data Index: 5763337 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8719. Min Act: -0.1700

Data Index: 5763375 (Open Web Text)

Max Activating Token Index: 645

Text #8

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8779. Min Act: -0.1700

Data Index: 5763350 (Open Web Text)

Max Activating Token Index: 796

Text #9

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8968. Min Act: -0.1700

Data Index: 5763355 (Open Web Text)

Max Activating Token Index: 806

Text #10

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8829. Min Act: -0.1700

Data Index: 5763371 (Open Web Text)

Max Activating Token Index: 869

Text #11

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8551. Min Act: -0.1700

Data Index: 5763361 (Open Web Text)

Max Activating Token Index: 866

Text #12

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8650. Min Act: -0.1700

Data Index: 5763359 (Open Web Text)

Max Activating Token Index: 971

Text #13

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8672. Min Act: -0.1700

Data Index: 5763366 (Open Web Text)

Max Activating Token Index: 955

Text #14

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8398. Min Act: -0.1700

Data Index: 5763364 (Open Web Text)

Max Activating Token Index: 877

Text #15

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8538. Min Act: -0.1700

Data Index: 5763357 (Open Web Text)

Max Activating Token Index: 849

Text #16

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8647. Min Act: -0.1700

Data Index: 5763362 (Open Web Text)

Max Activating Token Index: 938

Text #17

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8702. Min Act: -0.1700

Data Index: 5763352 (Open Web Text)

Max Activating Token Index: 938

Text #18

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8426. Min Act: -0.1700

Data Index: 5763351 (Open Web Text)

Max Activating Token Index: 870

Text #19

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8440. Min Act: -0.1700

Data Index: 5763363 (Open Web Text)

Max Activating Token Index: 766