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

Dataset: Open Web Text

Neuron 981 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: 4.6726. Min Range: -4.6726

Max Act: 4.6726. Min Act: -0.1700

Data Index: 2410602 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6111. Min Act: -0.1700

Data Index: 4248819 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6348. Min Act: -0.1700

Data Index: 88497 (Open Web Text)

Max Activating Token Index: 394

Text #3

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6223. Min Act: -0.1700

Data Index: 7646395 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5678. Min Act: -0.1700

Data Index: 3586402 (Open Web Text)

Max Activating Token Index: 395

Text #5

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5561. Min Act: -0.1700

Data Index: 8470743 (Open Web Text)

Max Activating Token Index: 630

Text #6

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5690. Min Act: -0.1700

Data Index: 6979503 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5348. Min Act: -0.1700

Data Index: 6048205 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5140. Min Act: -0.1700

Data Index: 7827300 (Open Web Text)

Max Activating Token Index: 907

Text #9

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5220. Min Act: -0.1700

Data Index: 5292083 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5305. Min Act: -0.1700

Data Index: 5195704 (Open Web Text)

Max Activating Token Index: 904

Text #11

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5510. Min Act: -0.1700

Data Index: 2843128 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5404. Min Act: -0.1700

Data Index: 2773015 (Open Web Text)

Max Activating Token Index: 365

Text #13

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5378. Min Act: -0.1700

Data Index: 5096458 (Open Web Text)

Max Activating Token Index: 771

Text #14

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5496. Min Act: -0.1700

Data Index: 4950845 (Open Web Text)

Max Activating Token Index: 685

Text #15

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5344. Min Act: -0.1700

Data Index: 7306581 (Open Web Text)

Max Activating Token Index: 689

Text #16

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5277. Min Act: -0.1700

Data Index: 7003526 (Open Web Text)

Max Activating Token Index: 527

Text #17

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5244. Min Act: -0.1700

Data Index: 6888018 (Open Web Text)

Max Activating Token Index: 888

Text #18

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5400. Min Act: -0.1700

Data Index: 2111821 (Open Web Text)

Max Activating Token Index: 775

Text #19

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5091. Min Act: -0.1700

Data Index: 5912801 (Open Web Text)

Max Activating Token Index: 727