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

Dataset: Open Web Text

Neuron 1587 in Layer 5

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: 4.4285. Min Range: -4.4285

Max Act: 4.4165. Min Act: -0.1700

Data Index: 4005500 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.4285. Min Act: -0.1700

Data Index: 7271741 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.4056. Min Act: -0.1700

Data Index: 1190453 (Open Web Text)

Max Activating Token Index: 258

Text #3

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3867. Min Act: -0.1700

Data Index: 3162209 (Open Web Text)

Max Activating Token Index: 495

Text #4

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3666. Min Act: -0.1700

Data Index: 6166741 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.4202. Min Act: -0.1700

Data Index: 2923921 (Open Web Text)

Max Activating Token Index: 480

Text #6

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3642. Min Act: -0.1700

Data Index: 5480500 (Open Web Text)

Max Activating Token Index: 199

Text #7

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3663. Min Act: -0.1700

Data Index: 5626714 (Open Web Text)

Max Activating Token Index: 118

Text #8

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3720. Min Act: -0.1700

Data Index: 2946893 (Open Web Text)

Max Activating Token Index: 614

Text #9

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3532. Min Act: -0.1700

Data Index: 2668670 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3170. Min Act: -0.1700

Data Index: 6563557 (Open Web Text)

Max Activating Token Index: 167

Text #11

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3570. Min Act: -0.1700

Data Index: 5063046 (Open Web Text)

Max Activating Token Index: 259

Text #12

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3401. Min Act: -0.1700

Data Index: 1132242 (Open Web Text)

Max Activating Token Index: 490

Text #13

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3580. Min Act: -0.1700

Data Index: 5796244 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3779. Min Act: -0.1700

Data Index: 6253673 (Open Web Text)

Max Activating Token Index: 195

Text #15

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3015. Min Act: -0.1700

Data Index: 6338037 (Open Web Text)

Max Activating Token Index: 863

Text #16

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.2792. Min Act: -0.1700

Data Index: 4624927 (Open Web Text)

Max Activating Token Index: 850

Text #17

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.2941. Min Act: -0.1700

Data Index: 1662008 (Open Web Text)

Max Activating Token Index: 525

Text #18

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3002. Min Act: -0.1700

Data Index: 5894291 (Open Web Text)

Max Activating Token Index: 70

Text #19

Max Range: 4.4285. Min Range: -4.4285

Max Act: 4.3264. Min Act: -0.1700

Data Index: 1329090 (Open Web Text)

Max Activating Token Index: 214