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

Dataset: Open Web Text

Neuron 632 in Layer 6

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: 6.7635. Min Range: -6.7635

Max Act: 6.7635. Min Act: -0.1700

Data Index: 3837311 (Open Web Text)

Max Activating Token Index: 896

Text #1

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.6613. Min Act: -0.1700

Data Index: 1650331 (Open Web Text)

Max Activating Token Index: 864

Text #2

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.6906. Min Act: -0.1700

Data Index: 8486974 (Open Web Text)

Max Activating Token Index: 426

Text #3

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.5394. Min Act: -0.1700

Data Index: 4508476 (Open Web Text)

Max Activating Token Index: 492

Text #4

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.5307. Min Act: -0.1700

Data Index: 5973090 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4901. Min Act: -0.1700

Data Index: 3072030 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4650. Min Act: -0.1700

Data Index: 8591723 (Open Web Text)

Max Activating Token Index: 532

Text #7

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.5153. Min Act: -0.1700

Data Index: 7185737 (Open Web Text)

Max Activating Token Index: 121

Text #8

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.5066. Min Act: -0.1700

Data Index: 3374745 (Open Web Text)

Max Activating Token Index: 269

Text #9

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4805. Min Act: -0.1700

Data Index: 8581291 (Open Web Text)

Max Activating Token Index: 279

Text #10

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4783. Min Act: -0.1700

Data Index: 5011497 (Open Web Text)

Max Activating Token Index: 669

Text #11

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4605. Min Act: -0.1700

Data Index: 4101384 (Open Web Text)

Max Activating Token Index: 862

Text #12

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4459. Min Act: -0.1700

Data Index: 1170238 (Open Web Text)

Max Activating Token Index: 589

Text #13

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4210. Min Act: -0.1700

Data Index: 6874188 (Open Web Text)

Max Activating Token Index: 378

Text #14

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4339. Min Act: -0.1700

Data Index: 4102022 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4478. Min Act: -0.1700

Data Index: 1147250 (Open Web Text)

Max Activating Token Index: 640

Text #16

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4009. Min Act: -0.1700

Data Index: 5305903 (Open Web Text)

Max Activating Token Index: 43

Text #17

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.4007. Min Act: -0.1700

Data Index: 7517175 (Open Web Text)

Max Activating Token Index: 268

Text #18

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.3736. Min Act: -0.1700

Data Index: 7820338 (Open Web Text)

Max Activating Token Index: 791

Text #19

Max Range: 6.7635. Min Range: -6.7635

Max Act: 6.3816. Min Act: -0.1700

Data Index: 1255407 (Open Web Text)

Max Activating Token Index: 231