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

Dataset: Open Web Text

Neuron 1325 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: 3.0590. Min Range: -3.0590

Max Act: 3.0590. Min Act: -0.1700

Data Index: 4836046 (Open Web Text)

Max Activating Token Index: 956

Text #1

Max Range: 3.0590. Min Range: -3.0590

Max Act: 3.0372. Min Act: -0.1700

Data Index: 3408320 (Open Web Text)

Max Activating Token Index: 570

Text #2

Max Range: 3.0590. Min Range: -3.0590

Max Act: 3.0300. Min Act: -0.1700

Data Index: 5509251 (Open Web Text)

Max Activating Token Index: 329

Text #3

Max Range: 3.0590. Min Range: -3.0590

Max Act: 3.0271. Min Act: -0.1700

Data Index: 3227664 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 3.0590. Min Range: -3.0590

Max Act: 3.0248. Min Act: -0.1700

Data Index: 1556740 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 3.0590. Min Range: -3.0590

Max Act: 3.0277. Min Act: -0.1700

Data Index: 3235922 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9990. Min Act: -0.1700

Data Index: 5076739 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 3.0590. Min Range: -3.0590

Max Act: 3.0195. Min Act: -0.1700

Data Index: 3571970 (Open Web Text)

Max Activating Token Index: 310

Text #8

Max Range: 3.0590. Min Range: -3.0590

Max Act: 3.0029. Min Act: -0.1700

Data Index: 5290001 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9978. Min Act: -0.1700

Data Index: 1940202 (Open Web Text)

Max Activating Token Index: 102

Text #10

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9774. Min Act: -0.1700

Data Index: 6505224 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9666. Min Act: -0.1700

Data Index: 247764 (Open Web Text)

Max Activating Token Index: 483

Text #12

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9872. Min Act: -0.1700

Data Index: 7886105 (Open Web Text)

Max Activating Token Index: 207

Text #13

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9491. Min Act: -0.1700

Data Index: 619559 (Open Web Text)

Max Activating Token Index: 219

Text #14

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9388. Min Act: -0.1700

Data Index: 4683253 (Open Web Text)

Max Activating Token Index: 93

Text #15

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9335. Min Act: -0.1700

Data Index: 3189945 (Open Web Text)

Max Activating Token Index: 510

Text #16

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9658. Min Act: -0.1700

Data Index: 6120227 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9438. Min Act: -0.1700

Data Index: 565079 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9405. Min Act: -0.1700

Data Index: 4156781 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.9414. Min Act: -0.1700

Data Index: 123287 (Open Web Text)

Max Activating Token Index: 611