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

Dataset: Open Web Text

Neuron 271 in Layer 2

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: 4.5890. Min Range: -4.5890

Max Act: 4.5890. Min Act: -0.1700

Data Index: 2398753 (Open Web Text)

Max Activating Token Index: 688

Text #1

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5819. Min Act: -0.1700

Data Index: 7327536 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5495. Min Act: -0.1700

Data Index: 5393677 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5629. Min Act: -0.1700

Data Index: 6011247 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5517. Min Act: -0.1700

Data Index: 4105459 (Open Web Text)

Max Activating Token Index: 801

Text #5

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5071. Min Act: -0.1700

Data Index: 3685830 (Open Web Text)

Max Activating Token Index: 581

Text #6

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5234. Min Act: -0.1700

Data Index: 7931077 (Open Web Text)

Max Activating Token Index: 657

Text #7

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5290. Min Act: -0.1700

Data Index: 4389435 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5289. Min Act: -0.1700

Data Index: 8504063 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5320. Min Act: -0.1700

Data Index: 170977 (Open Web Text)

Max Activating Token Index: 155

Text #10

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5172. Min Act: -0.1700

Data Index: 5883243 (Open Web Text)

Max Activating Token Index: 774

Text #11

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.5019. Min Act: -0.1700

Data Index: 3695154 (Open Web Text)

Max Activating Token Index: 491

Text #12

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.4843. Min Act: -0.1700

Data Index: 1807101 (Open Web Text)

Max Activating Token Index: 927

Text #13

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.4898. Min Act: -0.1700

Data Index: 8828865 (Open Web Text)

Max Activating Token Index: 737

Text #14

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.4509. Min Act: -0.1700

Data Index: 3555368 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.4429. Min Act: -0.1700

Data Index: 6908673 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.4600. Min Act: -0.1700

Data Index: 6998304 (Open Web Text)

Max Activating Token Index: 156

Text #17

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.4602. Min Act: -0.1700

Data Index: 6252760 (Open Web Text)

Max Activating Token Index: 564

Text #18

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.4678. Min Act: -0.1700

Data Index: 7746244 (Open Web Text)

Max Activating Token Index: 210

Text #19

Max Range: 4.5890. Min Range: -4.5890

Max Act: 4.4763. Min Act: -0.1700

Data Index: 4871110 (Open Web Text)

Max Activating Token Index: 630