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

Dataset: Open Web Text

Neuron 1062 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: 3.5174. Min Range: -3.5174

Max Act: 3.5174. Min Act: -0.1700

Data Index: 7785021 (Open Web Text)

Max Activating Token Index: 834

Text #1

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3548. Min Act: -0.1700

Data Index: 3408189 (Open Web Text)

Max Activating Token Index: 70

Text #2

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3761. Min Act: -0.1700

Data Index: 6917410 (Open Web Text)

Max Activating Token Index: 679

Text #3

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3751. Min Act: -0.1700

Data Index: 1406006 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3521. Min Act: -0.1700

Data Index: 1056941 (Open Web Text)

Max Activating Token Index: 587

Text #5

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2886. Min Act: -0.1700

Data Index: 7112843 (Open Web Text)

Max Activating Token Index: 643

Text #6

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3447. Min Act: -0.1700

Data Index: 4457987 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2992. Min Act: -0.1700

Data Index: 7375809 (Open Web Text)

Max Activating Token Index: 968

Text #8

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2760. Min Act: -0.1700

Data Index: 261252 (Open Web Text)

Max Activating Token Index: 204

Text #9

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2785. Min Act: -0.1700

Data Index: 3616877 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2992. Min Act: -0.1700

Data Index: 5459269 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3033. Min Act: -0.1700

Data Index: 4413328 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2790. Min Act: -0.1700

Data Index: 4232475 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2779. Min Act: -0.1700

Data Index: 3456162 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2534. Min Act: -0.1700

Data Index: 5190040 (Open Web Text)

Max Activating Token Index: 979

Text #15

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2483. Min Act: -0.1700

Data Index: 457563 (Open Web Text)

Max Activating Token Index: 38

Text #16

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2888. Min Act: -0.1700

Data Index: 132827 (Open Web Text)

Max Activating Token Index: 643

Text #17

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2414. Min Act: -0.1700

Data Index: 7448029 (Open Web Text)

Max Activating Token Index: 865

Text #18

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2967. Min Act: -0.1700

Data Index: 4866599 (Open Web Text)

Max Activating Token Index: 659

Text #19

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2677. Min Act: -0.1700

Data Index: 2180501 (Open Web Text)

Max Activating Token Index: 18