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

Dataset: Open Web Text

Neuron 2216 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: 3.3561. Min Range: -3.3561

Max Act: 3.3432. Min Act: -0.1700

Data Index: 8153889 (Open Web Text)

Max Activating Token Index: 614

Text #1

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3561. Min Act: -0.1700

Data Index: 8432580 (Open Web Text)

Max Activating Token Index: 552

Text #2

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3405. Min Act: -0.1700

Data Index: 1397833 (Open Web Text)

Max Activating Token Index: 575

Text #3

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3361. Min Act: -0.1700

Data Index: 6018223 (Open Web Text)

Max Activating Token Index: 871

Text #4

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3210. Min Act: -0.1700

Data Index: 6543293 (Open Web Text)

Max Activating Token Index: 156

Text #5

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3080. Min Act: -0.1700

Data Index: 2593975 (Open Web Text)

Max Activating Token Index: 456

Text #6

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3162. Min Act: -0.1700

Data Index: 1310509 (Open Web Text)

Max Activating Token Index: 783

Text #7

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3021. Min Act: -0.1700

Data Index: 6712535 (Open Web Text)

Max Activating Token Index: 580

Text #8

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2995. Min Act: -0.1700

Data Index: 5927337 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2695. Min Act: -0.1700

Data Index: 855653 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2924. Min Act: -0.1700

Data Index: 704656 (Open Web Text)

Max Activating Token Index: 130

Text #11

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2797. Min Act: -0.1700

Data Index: 4254542 (Open Web Text)

Max Activating Token Index: 473

Text #12

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2681. Min Act: -0.1700

Data Index: 84134 (Open Web Text)

Max Activating Token Index: 572

Text #13

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2889. Min Act: -0.1700

Data Index: 535992 (Open Web Text)

Max Activating Token Index: 449

Text #14

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2710. Min Act: -0.1700

Data Index: 8092216 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2775. Min Act: -0.1700

Data Index: 7520075 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2561. Min Act: -0.1700

Data Index: 7731623 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2566. Min Act: -0.1700

Data Index: 2488013 (Open Web Text)

Max Activating Token Index: 231

Text #18

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2592. Min Act: -0.1700

Data Index: 5064916 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2544. Min Act: -0.1700

Data Index: 7397990 (Open Web Text)

Max Activating Token Index: 380