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

Dataset: Open Web Text

Neuron 2131 in Layer 6

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: 6.1181. Min Range: -6.1181

Max Act: 6.1181. Min Act: -0.1700

Data Index: 1830018 (Open Web Text)

Max Activating Token Index: 641

Text #1

Max Range: 6.1181. Min Range: -6.1181

Max Act: 6.1127. Min Act: -0.1700

Data Index: 8140686 (Open Web Text)

Max Activating Token Index: 783

Text #2

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.9074. Min Act: -0.1700

Data Index: 7038021 (Open Web Text)

Max Activating Token Index: 265

Text #3

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.9556. Min Act: -0.1700

Data Index: 1945182 (Open Web Text)

Max Activating Token Index: 930

Text #4

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.9074. Min Act: -0.1700

Data Index: 2982346 (Open Web Text)

Max Activating Token Index: 709

Text #5

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8925. Min Act: -0.1700

Data Index: 2932818 (Open Web Text)

Max Activating Token Index: 398

Text #6

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.9321. Min Act: -0.1700

Data Index: 1188573 (Open Web Text)

Max Activating Token Index: 206

Text #7

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.9279. Min Act: -0.1700

Data Index: 233894 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8839. Min Act: -0.1700

Data Index: 4055542 (Open Web Text)

Max Activating Token Index: 968

Text #9

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8661. Min Act: -0.1700

Data Index: 6683849 (Open Web Text)

Max Activating Token Index: 556

Text #10

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.9185. Min Act: -0.1700

Data Index: 2228333 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8625. Min Act: -0.1700

Data Index: 56904 (Open Web Text)

Max Activating Token Index: 244

Text #12

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8798. Min Act: -0.1700

Data Index: 2113133 (Open Web Text)

Max Activating Token Index: 362

Text #13

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8679. Min Act: -0.1700

Data Index: 3019946 (Open Web Text)

Max Activating Token Index: 324

Text #14

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8840. Min Act: -0.1700

Data Index: 8191303 (Open Web Text)

Max Activating Token Index: 438

Text #15

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8855. Min Act: -0.1700

Data Index: 6645323 (Open Web Text)

Max Activating Token Index: 376

Text #16

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8405. Min Act: -0.1700

Data Index: 2072736 (Open Web Text)

Max Activating Token Index: 318

Text #17

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8458. Min Act: -0.1700

Data Index: 4055022 (Open Web Text)

Max Activating Token Index: 225

Text #18

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8417. Min Act: -0.1700

Data Index: 5720770 (Open Web Text)

Max Activating Token Index: 398

Text #19

Max Range: 6.1181. Min Range: -6.1181

Max Act: 5.8625. Min Act: -0.1700

Data Index: 1720867 (Open Web Text)

Max Activating Token Index: 364