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

Dataset: Open Web Text

Neuron 993 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: 3.4715. Min Range: -3.4715

Max Act: 3.4715. Min Act: -0.1700

Data Index: 154537 (Open Web Text)

Max Activating Token Index: 890

Text #1

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4633. Min Act: -0.1700

Data Index: 7858483 (Open Web Text)

Max Activating Token Index: 317

Text #2

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4655. Min Act: -0.1700

Data Index: 5956446 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4383. Min Act: -0.1700

Data Index: 4997440 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4474. Min Act: -0.1700

Data Index: 4351675 (Open Web Text)

Max Activating Token Index: 921

Text #5

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4453. Min Act: -0.1700

Data Index: 29794 (Open Web Text)

Max Activating Token Index: 268

Text #6

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4194. Min Act: -0.1700

Data Index: 2217049 (Open Web Text)

Max Activating Token Index: 712

Text #7

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4220. Min Act: -0.1700

Data Index: 4246558 (Open Web Text)

Max Activating Token Index: 147

Text #8

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4384. Min Act: -0.1700

Data Index: 5600734 (Open Web Text)

Max Activating Token Index: 861

Text #9

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.3945. Min Act: -0.1700

Data Index: 5821142 (Open Web Text)

Max Activating Token Index: 442

Text #10

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4221. Min Act: -0.1700

Data Index: 1250247 (Open Web Text)

Max Activating Token Index: 976

Text #11

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.3670. Min Act: -0.1700

Data Index: 2082247 (Open Web Text)

Max Activating Token Index: 721

Text #12

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.3793. Min Act: -0.1700

Data Index: 6530256 (Open Web Text)

Max Activating Token Index: 791

Text #13

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.4056. Min Act: -0.1700

Data Index: 365771 (Open Web Text)

Max Activating Token Index: 697

Text #14

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.3673. Min Act: -0.1700

Data Index: 6364990 (Open Web Text)

Max Activating Token Index: 249

Text #15

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.3700. Min Act: -0.1700

Data Index: 5188021 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.2515. Min Act: -0.1700

Data Index: 7034860 (Open Web Text)

Max Activating Token Index: 599

Text #17

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.3429. Min Act: -0.1700

Data Index: 5380189 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.3663. Min Act: -0.1700

Data Index: 1468200 (Open Web Text)

Max Activating Token Index: 251

Text #19

Max Range: 3.4715. Min Range: -3.4715

Max Act: 3.3133. Min Act: -0.1700

Data Index: 5840066 (Open Web Text)

Max Activating Token Index: 306