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

Dataset: Open Web Text

Neuron 690 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: 5.1639. Min Range: -5.1639

Max Act: 5.1639. Min Act: -0.1700

Data Index: 501094 (Open Web Text)

Max Activating Token Index: 667

Text #1

Max Range: 5.1639. Min Range: -5.1639

Max Act: 5.0149. Min Act: -0.1700

Data Index: 7423075 (Open Web Text)

Max Activating Token Index: 307

Text #2

Max Range: 5.1639. Min Range: -5.1639

Max Act: 5.0253. Min Act: -0.1700

Data Index: 5386091 (Open Web Text)

Max Activating Token Index: 337

Text #3

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.9902. Min Act: -0.1700

Data Index: 8339269 (Open Web Text)

Max Activating Token Index: 850

Text #4

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.9030. Min Act: -0.1700

Data Index: 3583431 (Open Web Text)

Max Activating Token Index: 26

Text #5

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8700. Min Act: -0.1700

Data Index: 5675617 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.9187. Min Act: -0.1700

Data Index: 7669240 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8690. Min Act: -0.1700

Data Index: 2941794 (Open Web Text)

Max Activating Token Index: 926

Text #8

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8780. Min Act: -0.1700

Data Index: 218369 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8761. Min Act: -0.1700

Data Index: 1751799 (Open Web Text)

Max Activating Token Index: 469

Text #10

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8497. Min Act: -0.1700

Data Index: 7025385 (Open Web Text)

Max Activating Token Index: 317

Text #11

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8708. Min Act: -0.1700

Data Index: 8628604 (Open Web Text)

Max Activating Token Index: 124

Text #12

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8667. Min Act: -0.1700

Data Index: 452139 (Open Web Text)

Max Activating Token Index: 341

Text #13

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8756. Min Act: -0.1700

Data Index: 8164309 (Open Web Text)

Max Activating Token Index: 659

Text #14

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8109. Min Act: -0.1700

Data Index: 5280354 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.7783. Min Act: -0.1700

Data Index: 8117198 (Open Web Text)

Max Activating Token Index: 658

Text #16

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8239. Min Act: -0.1700

Data Index: 3915942 (Open Web Text)

Max Activating Token Index: 166

Text #17

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.7815. Min Act: -0.1700

Data Index: 8782917 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.7967. Min Act: -0.1700

Data Index: 970782 (Open Web Text)

Max Activating Token Index: 589

Text #19

Max Range: 5.1639. Min Range: -5.1639

Max Act: 4.8037. Min Act: -0.1700

Data Index: 5432218 (Open Web Text)

Max Activating Token Index: 689