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

Dataset: Open Web Text

Neuron 1687 in Layer 3

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: 5.0684. Min Range: -5.0684

Max Act: 5.0114. Min Act: -0.1700

Data Index: 6954507 (Open Web Text)

Max Activating Token Index: 176

Text #1

Max Range: 5.0684. Min Range: -5.0684

Max Act: 5.0684. Min Act: -0.1700

Data Index: 6949790 (Open Web Text)

Max Activating Token Index: 913

Text #2

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.9872. Min Act: -0.1700

Data Index: 6075698 (Open Web Text)

Max Activating Token Index: 402

Text #3

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.9648. Min Act: -0.1700

Data Index: 2723450 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.9433. Min Act: -0.1700

Data Index: 292476 (Open Web Text)

Max Activating Token Index: 315

Text #5

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.9017. Min Act: -0.1700

Data Index: 4839161 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.9191. Min Act: -0.1700

Data Index: 6061165 (Open Web Text)

Max Activating Token Index: 885

Text #7

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8368. Min Act: -0.1700

Data Index: 2623651 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8507. Min Act: -0.1700

Data Index: 432371 (Open Web Text)

Max Activating Token Index: 364

Text #9

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8699. Min Act: -0.1700

Data Index: 6036827 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8406. Min Act: -0.1700

Data Index: 5970561 (Open Web Text)

Max Activating Token Index: 834

Text #11

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8193. Min Act: -0.1700

Data Index: 5660157 (Open Web Text)

Max Activating Token Index: 483

Text #12

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8483. Min Act: -0.1700

Data Index: 8024680 (Open Web Text)

Max Activating Token Index: 793

Text #13

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8583. Min Act: -0.1700

Data Index: 7996289 (Open Web Text)

Max Activating Token Index: 502

Text #14

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8681. Min Act: -0.1700

Data Index: 6861008 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8328. Min Act: -0.1700

Data Index: 3517567 (Open Web Text)

Max Activating Token Index: 867

Text #16

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8266. Min Act: -0.1700

Data Index: 3376916 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.7654. Min Act: -0.1700

Data Index: 6308057 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8362. Min Act: -0.1700

Data Index: 8055876 (Open Web Text)

Max Activating Token Index: 752

Text #19

Max Range: 5.0684. Min Range: -5.0684

Max Act: 4.8105. Min Act: -0.1700

Data Index: 4770612 (Open Web Text)

Max Activating Token Index: 197