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

Dataset: Open Web Text

Neuron 1151 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: 4.2591. Min Range: -4.2591

Max Act: 4.2591. Min Act: -0.1700

Data Index: 497607 (Open Web Text)

Max Activating Token Index: 896

Text #1

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1980. Min Act: -0.1700

Data Index: 6791825 (Open Web Text)

Max Activating Token Index: 379

Text #2

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1886. Min Act: -0.1700

Data Index: 4755246 (Open Web Text)

Max Activating Token Index: 564

Text #3

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1653. Min Act: -0.1700

Data Index: 2809017 (Open Web Text)

Max Activating Token Index: 183

Text #4

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1636. Min Act: -0.1700

Data Index: 1870749 (Open Web Text)

Max Activating Token Index: 619

Text #5

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1576. Min Act: -0.1700

Data Index: 7991142 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1561. Min Act: -0.1700

Data Index: 5071380 (Open Web Text)

Max Activating Token Index: 480

Text #7

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1477. Min Act: -0.1700

Data Index: 271020 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1203. Min Act: -0.1700

Data Index: 3264192 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1498. Min Act: -0.1700

Data Index: 7363057 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1217. Min Act: -0.1700

Data Index: 7390146 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1032. Min Act: -0.1700

Data Index: 6252440 (Open Web Text)

Max Activating Token Index: 669

Text #12

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0910. Min Act: -0.1700

Data Index: 7119104 (Open Web Text)

Max Activating Token Index: 224

Text #13

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1012. Min Act: -0.1700

Data Index: 1486300 (Open Web Text)

Max Activating Token Index: 530

Text #14

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0844. Min Act: -0.1700

Data Index: 7130821 (Open Web Text)

Max Activating Token Index: 302

Text #15

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0697. Min Act: -0.1700

Data Index: 5772878 (Open Web Text)

Max Activating Token Index: 741

Text #16

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0701. Min Act: -0.1700

Data Index: 285196 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0756. Min Act: -0.1700

Data Index: 7113255 (Open Web Text)

Max Activating Token Index: 113

Text #18

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0757. Min Act: -0.1700

Data Index: 3948916 (Open Web Text)

Max Activating Token Index: 716

Text #19

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0769. Min Act: -0.1700

Data Index: 3632044 (Open Web Text)

Max Activating Token Index: 142