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

Dataset: Open Web Text

Neuron 2383 in Layer 1

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: 1.1581. Min Range: -1.1581

Max Act: 1.1581. Min Act: -0.1518

Data Index: 2170284 (Open Web Text)

Max Activating Token Index: 126

Text #1

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.1558. Min Act: -0.1612

Data Index: 2170286 (Open Web Text)

Max Activating Token Index: 346

Text #2

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.1089. Min Act: -0.1461

Data Index: 2170285 (Open Web Text)

Max Activating Token Index: 129

Text #3

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0929. Min Act: -0.1579

Data Index: 2184939 (Open Web Text)

Max Activating Token Index: 327

Text #4

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0901. Min Act: -0.1649

Data Index: 2170288 (Open Web Text)

Max Activating Token Index: 313

Text #5

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0914. Min Act: -0.1700

Data Index: 81453 (Open Web Text)

Max Activating Token Index: 231

Text #6

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0852. Min Act: -0.1699

Data Index: 3978259 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0930. Min Act: -0.1699

Data Index: 2170287 (Open Web Text)

Max Activating Token Index: 272

Text #8

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0909. Min Act: -0.1636

Data Index: 6033350 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0809. Min Act: -0.1700

Data Index: 7398385 (Open Web Text)

Max Activating Token Index: 902

Text #10

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0788. Min Act: -0.1699

Data Index: 4699442 (Open Web Text)

Max Activating Token Index: 444

Text #11

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0762. Min Act: -0.1698

Data Index: 5637786 (Open Web Text)

Max Activating Token Index: 312

Text #12

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0829. Min Act: -0.1162

Data Index: 3083728 (Open Web Text)

Max Activating Token Index: 400

Text #13

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0709. Min Act: -0.1373

Data Index: 2170283 (Open Web Text)

Max Activating Token Index: 522

Text #14

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0676. Min Act: -0.1700

Data Index: 5985880 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0622. Min Act: -0.1011

Data Index: 3083729 (Open Web Text)

Max Activating Token Index: 350

Text #16

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0448. Min Act: -0.1669

Data Index: 5210325 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0559. Min Act: -0.1691

Data Index: 8296620 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0504. Min Act: -0.1501

Data Index: 5838920 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0519. Min Act: -0.1535

Data Index: 4833496 (Open Web Text)

Max Activating Token Index: 370