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

Dataset: Open Web Text

Neuron 1336 in Layer 0

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: 4.9743. Min Range: -4.9743

Max Act: 4.9743. Min Act: -0.1700

Data Index: 8076110 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.9417. Min Act: -0.1700

Data Index: 3817575 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.9592. Min Act: -0.1700

Data Index: 3141940 (Open Web Text)

Max Activating Token Index: 795

Text #3

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.9018. Min Act: -0.1700

Data Index: 3828819 (Open Web Text)

Max Activating Token Index: 828

Text #4

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.9136. Min Act: -0.1700

Data Index: 2367564 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.8843. Min Act: -0.1700

Data Index: 1427990 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.8968. Min Act: -0.1700

Data Index: 5103639 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.8729. Min Act: -0.1700

Data Index: 4729799 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.8390. Min Act: -0.1700

Data Index: 6409132 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.8197. Min Act: -0.1700

Data Index: 3010819 (Open Web Text)

Max Activating Token Index: 718

Text #10

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.7969. Min Act: -0.1700

Data Index: 1451002 (Open Web Text)

Max Activating Token Index: 892

Text #11

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.8096. Min Act: -0.1700

Data Index: 8510040 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.8102. Min Act: -0.1700

Data Index: 3356363 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.8000. Min Act: -0.1700

Data Index: 1057502 (Open Web Text)

Max Activating Token Index: 795

Text #14

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.8042. Min Act: -0.1700

Data Index: 2532284 (Open Web Text)

Max Activating Token Index: 876

Text #15

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.7776. Min Act: -0.1700

Data Index: 1965350 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.7850. Min Act: -0.1700

Data Index: 7587643 (Open Web Text)

Max Activating Token Index: 749

Text #17

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.7699. Min Act: -0.1700

Data Index: 6896360 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.7265. Min Act: -0.1700

Data Index: 2154025 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.9743. Min Range: -4.9743

Max Act: 4.7398. Min Act: -0.1700

Data Index: 5517660 (Open Web Text)

Max Activating Token Index: 184