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

Dataset: Open Web Text

Neuron 1709 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: 4.8863. Min Range: -4.8863

Max Act: 4.8694. Min Act: -0.1700

Data Index: 5439711 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.8863. Min Act: -0.1700

Data Index: 1880455 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.8515. Min Act: -0.1700

Data Index: 8415351 (Open Web Text)

Max Activating Token Index: 239

Text #3

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.8828. Min Act: -0.1700

Data Index: 4834208 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.8101. Min Act: -0.1700

Data Index: 1230574 (Open Web Text)

Max Activating Token Index: 656

Text #5

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.8159. Min Act: -0.1700

Data Index: 1672199 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7977. Min Act: -0.1700

Data Index: 5233352 (Open Web Text)

Max Activating Token Index: 245

Text #7

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7628. Min Act: -0.1700

Data Index: 4331127 (Open Web Text)

Max Activating Token Index: 833

Text #8

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7624. Min Act: -0.1700

Data Index: 4969133 (Open Web Text)

Max Activating Token Index: 812

Text #9

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7637. Min Act: -0.1700

Data Index: 7047591 (Open Web Text)

Max Activating Token Index: 535

Text #10

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7540. Min Act: -0.1700

Data Index: 2962330 (Open Web Text)

Max Activating Token Index: 856

Text #11

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7749. Min Act: -0.1700

Data Index: 985590 (Open Web Text)

Max Activating Token Index: 204

Text #12

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7619. Min Act: -0.1700

Data Index: 4327003 (Open Web Text)

Max Activating Token Index: 265

Text #13

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.6920. Min Act: -0.1700

Data Index: 312625 (Open Web Text)

Max Activating Token Index: 722

Text #14

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7389. Min Act: -0.1700

Data Index: 7572952 (Open Web Text)

Max Activating Token Index: 776

Text #15

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7243. Min Act: -0.1700

Data Index: 4207539 (Open Web Text)

Max Activating Token Index: 851

Text #16

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.6951. Min Act: -0.1700

Data Index: 7518338 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7013. Min Act: -0.1700

Data Index: 3584464 (Open Web Text)

Max Activating Token Index: 259

Text #18

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.7234. Min Act: -0.1700

Data Index: 7364547 (Open Web Text)

Max Activating Token Index: 366

Text #19

Max Range: 4.8863. Min Range: -4.8863

Max Act: 4.6619. Min Act: -0.1700

Data Index: 1911368 (Open Web Text)

Max Activating Token Index: 327