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

Dataset: Open Web Text

Neuron 34 in Layer 6

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: 5.8168. Min Range: -5.8168

Max Act: 5.8168. Min Act: -0.1700

Data Index: 2916424 (Open Web Text)

Max Activating Token Index: 335

Text #1

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.7762. Min Act: -0.1700

Data Index: 453896 (Open Web Text)

Max Activating Token Index: 786

Text #2

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.7721. Min Act: -0.1700

Data Index: 2529387 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.7406. Min Act: -0.1700

Data Index: 454910 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.7464. Min Act: -0.1700

Data Index: 5645573 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.7432. Min Act: -0.1700

Data Index: 7872355 (Open Web Text)

Max Activating Token Index: 991

Text #6

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.7667. Min Act: -0.1700

Data Index: 3842154 (Open Web Text)

Max Activating Token Index: 753

Text #7

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.7083. Min Act: -0.1700

Data Index: 5008017 (Open Web Text)

Max Activating Token Index: 374

Text #8

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.7087. Min Act: -0.1700

Data Index: 1812699 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.7069. Min Act: -0.1700

Data Index: 2826338 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.6700. Min Act: -0.1700

Data Index: 1040584 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.6784. Min Act: -0.1700

Data Index: 3273383 (Open Web Text)

Max Activating Token Index: 807

Text #12

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.6876. Min Act: -0.1700

Data Index: 4736575 (Open Web Text)

Max Activating Token Index: 333

Text #13

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.6794. Min Act: -0.1700

Data Index: 3785900 (Open Web Text)

Max Activating Token Index: 804

Text #14

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.6397. Min Act: -0.1700

Data Index: 3156526 (Open Web Text)

Max Activating Token Index: 603

Text #15

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.6600. Min Act: -0.1700

Data Index: 4652204 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.6199. Min Act: -0.1700

Data Index: 84906 (Open Web Text)

Max Activating Token Index: 907

Text #17

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.5939. Min Act: -0.1700

Data Index: 5137418 (Open Web Text)

Max Activating Token Index: 289

Text #18

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.6001. Min Act: -0.1700

Data Index: 661711 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 5.8168. Min Range: -5.8168

Max Act: 5.5910. Min Act: -0.1700

Data Index: 3280101 (Open Web Text)

Max Activating Token Index: 805