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

Dataset: Open Web Text

Neuron 2360 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: 7.4564. Min Range: -7.4564

Max Act: 7.4564. Min Act: -0.1700

Data Index: 4922695 (Open Web Text)

Max Activating Token Index: 482

Text #1

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.3160. Min Act: -0.1700

Data Index: 3211573 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.3119. Min Act: -0.1700

Data Index: 5906193 (Open Web Text)

Max Activating Token Index: 158

Text #3

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.2343. Min Act: -0.1700

Data Index: 5094775 (Open Web Text)

Max Activating Token Index: 387

Text #4

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.2491. Min Act: -0.1700

Data Index: 1014642 (Open Web Text)

Max Activating Token Index: 705

Text #5

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.2011. Min Act: -0.1700

Data Index: 8777597 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.1781. Min Act: -0.1700

Data Index: 7262793 (Open Web Text)

Max Activating Token Index: 966

Text #7

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.1015. Min Act: -0.1700

Data Index: 1431762 (Open Web Text)

Max Activating Token Index: 161

Text #8

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.1128. Min Act: -0.1700

Data Index: 1007216 (Open Web Text)

Max Activating Token Index: 658

Text #9

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0876. Min Act: -0.1700

Data Index: 55810 (Open Web Text)

Max Activating Token Index: 836

Text #10

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.1493. Min Act: -0.1700

Data Index: 6381403 (Open Web Text)

Max Activating Token Index: 723

Text #11

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0927. Min Act: -0.1700

Data Index: 3118939 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0535. Min Act: -0.1700

Data Index: 8078218 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0781. Min Act: -0.1700

Data Index: 1489096 (Open Web Text)

Max Activating Token Index: 997

Text #14

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0330. Min Act: -0.1700

Data Index: 4600910 (Open Web Text)

Max Activating Token Index: 610

Text #15

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0380. Min Act: -0.1700

Data Index: 3030638 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0652. Min Act: -0.1700

Data Index: 4897437 (Open Web Text)

Max Activating Token Index: 149

Text #17

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0861. Min Act: -0.1700

Data Index: 1475470 (Open Web Text)

Max Activating Token Index: 284

Text #18

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0783. Min Act: -0.1700

Data Index: 6353591 (Open Web Text)

Max Activating Token Index: 679

Text #19

Max Range: 7.4564. Min Range: -7.4564

Max Act: 7.0752. Min Act: -0.1700

Data Index: 2577329 (Open Web Text)

Max Activating Token Index: 568