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

Dataset: Open Web Text

Neuron 649 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: 2.9016. Min Range: -2.9016

Max Act: 2.9016. Min Act: -0.1700

Data Index: 5686340 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.8632. Min Act: -0.1700

Data Index: 3497871 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.7894. Min Act: -0.1700

Data Index: 3686475 (Open Web Text)

Max Activating Token Index: 834

Text #3

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.7544. Min Act: -0.1694

Data Index: 2859831 (Open Web Text)

Max Activating Token Index: 277

Text #4

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.7480. Min Act: -0.1700

Data Index: 6880502 (Open Web Text)

Max Activating Token Index: 583

Text #5

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.7459. Min Act: -0.1700

Data Index: 7709903 (Open Web Text)

Max Activating Token Index: 249

Text #6

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.7204. Min Act: -0.1700

Data Index: 2102463 (Open Web Text)

Max Activating Token Index: 599

Text #7

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.7002. Min Act: -0.1700

Data Index: 7589119 (Open Web Text)

Max Activating Token Index: 271

Text #8

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.7026. Min Act: -0.1700

Data Index: 3303277 (Open Web Text)

Max Activating Token Index: 685

Text #9

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.6799. Min Act: -0.1700

Data Index: 5364552 (Open Web Text)

Max Activating Token Index: 291

Text #10

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.6936. Min Act: -0.1700

Data Index: 4863965 (Open Web Text)

Max Activating Token Index: 781

Text #11

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.6481. Min Act: -0.1700

Data Index: 1355767 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.6188. Min Act: -0.1700

Data Index: 2859847 (Open Web Text)

Max Activating Token Index: 214

Text #13

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.6091. Min Act: -0.1700

Data Index: 810369 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.5969. Min Act: -0.1700

Data Index: 3770669 (Open Web Text)

Max Activating Token Index: 896

Text #15

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.6089. Min Act: -0.1700

Data Index: 3032994 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.5980. Min Act: -0.1700

Data Index: 1076504 (Open Web Text)

Max Activating Token Index: 823

Text #17

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.6171. Min Act: -0.1700

Data Index: 5158478 (Open Web Text)

Max Activating Token Index: 776

Text #18

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.5897. Min Act: -0.1698

Data Index: 2445165 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.9016. Min Range: -2.9016

Max Act: 2.5869. Min Act: -0.1700

Data Index: 2594601 (Open Web Text)

Max Activating Token Index: 555