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

Dataset: Open Web Text

Neuron 1512 in Layer 2

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: 5.7062. Min Range: -5.7062

Max Act: 5.7062. Min Act: -0.1700

Data Index: 2821192 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.7034. Min Act: -0.1700

Data Index: 5076884 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6876. Min Act: -0.1700

Data Index: 6983569 (Open Web Text)

Max Activating Token Index: 229

Text #3

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6863. Min Act: -0.1700

Data Index: 3149124 (Open Web Text)

Max Activating Token Index: 464

Text #4

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6677. Min Act: -0.1700

Data Index: 5719090 (Open Web Text)

Max Activating Token Index: 901

Text #5

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6711. Min Act: -0.1700

Data Index: 829249 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6627. Min Act: -0.1700

Data Index: 3134706 (Open Web Text)

Max Activating Token Index: 737

Text #7

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6257. Min Act: -0.1700

Data Index: 3358898 (Open Web Text)

Max Activating Token Index: 370

Text #8

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6073. Min Act: -0.1700

Data Index: 5533751 (Open Web Text)

Max Activating Token Index: 446

Text #9

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6102. Min Act: -0.1700

Data Index: 2602544 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6129. Min Act: -0.1700

Data Index: 205425 (Open Web Text)

Max Activating Token Index: 661

Text #11

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.5896. Min Act: -0.1700

Data Index: 603429 (Open Web Text)

Max Activating Token Index: 400

Text #12

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6224. Min Act: -0.1700

Data Index: 1205395 (Open Web Text)

Max Activating Token Index: 327

Text #13

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6183. Min Act: -0.1700

Data Index: 3016274 (Open Web Text)

Max Activating Token Index: 498

Text #14

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6344. Min Act: -0.1700

Data Index: 2967216 (Open Web Text)

Max Activating Token Index: 228

Text #15

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.6341. Min Act: -0.1700

Data Index: 6786428 (Open Web Text)

Max Activating Token Index: 242

Text #16

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.5653. Min Act: -0.1700

Data Index: 5012702 (Open Web Text)

Max Activating Token Index: 859

Text #17

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.5656. Min Act: -0.1700

Data Index: 2322882 (Open Web Text)

Max Activating Token Index: 741

Text #18

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.5656. Min Act: -0.1700

Data Index: 3998936 (Open Web Text)

Max Activating Token Index: 162

Text #19

Max Range: 5.7062. Min Range: -5.7062

Max Act: 5.5725. Min Act: -0.1700

Data Index: 2543284 (Open Web Text)

Max Activating Token Index: 999