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

Dataset: Open Web Text

Neuron 1038 in Layer 4

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: 4.1144. Min Range: -4.1144

Max Act: 4.1144. Min Act: -0.1700

Data Index: 4256372 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.9216. Min Act: -0.1700

Data Index: 5685625 (Open Web Text)

Max Activating Token Index: 644

Text #2

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.7047. Min Act: -0.1700

Data Index: 402487 (Open Web Text)

Max Activating Token Index: 564

Text #3

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.6743. Min Act: -0.1700

Data Index: 1628569 (Open Web Text)

Max Activating Token Index: 739

Text #4

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.6185. Min Act: -0.1700

Data Index: 8685726 (Open Web Text)

Max Activating Token Index: 603

Text #5

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.6108. Min Act: -0.1700

Data Index: 6012062 (Open Web Text)

Max Activating Token Index: 788

Text #6

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.5818. Min Act: -0.1700

Data Index: 4354250 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.5720. Min Act: -0.1700

Data Index: 6334359 (Open Web Text)

Max Activating Token Index: 969

Text #8

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.5814. Min Act: -0.1700

Data Index: 6880332 (Open Web Text)

Max Activating Token Index: 618

Text #9

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.5421. Min Act: -0.1700

Data Index: 5696808 (Open Web Text)

Max Activating Token Index: 970

Text #10

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.4920. Min Act: -0.1700

Data Index: 7846617 (Open Web Text)

Max Activating Token Index: 266

Text #11

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.4970. Min Act: -0.1700

Data Index: 374562 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.4902. Min Act: -0.1700

Data Index: 152574 (Open Web Text)

Max Activating Token Index: 819

Text #13

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.3967. Min Act: -0.1700

Data Index: 1838595 (Open Web Text)

Max Activating Token Index: 546

Text #14

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.4195. Min Act: -0.1700

Data Index: 3471758 (Open Web Text)

Max Activating Token Index: 62

Text #15

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.4395. Min Act: -0.1700

Data Index: 7135422 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.4361. Min Act: -0.1700

Data Index: 6579350 (Open Web Text)

Max Activating Token Index: 214

Text #17

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.3882. Min Act: -0.1700

Data Index: 5134881 (Open Web Text)

Max Activating Token Index: 621

Text #18

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.4089. Min Act: -0.1700

Data Index: 522089 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.4073. Min Act: -0.1700

Data Index: 5470171 (Open Web Text)

Max Activating Token Index: 629