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

Dataset: Open Web Text

Neuron 299 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: 3.1184. Min Range: -3.1184

Max Act: 3.1184. Min Act: -0.1700

Data Index: 665321 (Open Web Text)

Max Activating Token Index: 619

Text #1

Max Range: 3.1184. Min Range: -3.1184

Max Act: 3.0651. Min Act: -0.1700

Data Index: 4222202 (Open Web Text)

Max Activating Token Index: 715

Text #2

Max Range: 3.1184. Min Range: -3.1184

Max Act: 3.0309. Min Act: -0.1700

Data Index: 2757782 (Open Web Text)

Max Activating Token Index: 745

Text #3

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9999. Min Act: -0.1700

Data Index: 8297166 (Open Web Text)

Max Activating Token Index: 301

Text #4

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9906. Min Act: -0.1700

Data Index: 5723028 (Open Web Text)

Max Activating Token Index: 587

Text #5

Max Range: 3.1184. Min Range: -3.1184

Max Act: 3.0064. Min Act: -0.1700

Data Index: 5921039 (Open Web Text)

Max Activating Token Index: 686

Text #6

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9717. Min Act: -0.1700

Data Index: 3178035 (Open Web Text)

Max Activating Token Index: 134

Text #7

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9801. Min Act: -0.1700

Data Index: 5606224 (Open Web Text)

Max Activating Token Index: 833

Text #8

Max Range: 3.1184. Min Range: -3.1184

Max Act: 3.0029. Min Act: -0.1700

Data Index: 6584444 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9695. Min Act: -0.1700

Data Index: 5972679 (Open Web Text)

Max Activating Token Index: 665

Text #10

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9656. Min Act: -0.1700

Data Index: 6969102 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9723. Min Act: -0.1700

Data Index: 3927308 (Open Web Text)

Max Activating Token Index: 634

Text #12

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9785. Min Act: -0.1700

Data Index: 6049253 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9767. Min Act: -0.1700

Data Index: 1198595 (Open Web Text)

Max Activating Token Index: 829

Text #14

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9388. Min Act: -0.1700

Data Index: 6754521 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9354. Min Act: -0.1700

Data Index: 7199865 (Open Web Text)

Max Activating Token Index: 857

Text #16

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9568. Min Act: -0.1700

Data Index: 7741001 (Open Web Text)

Max Activating Token Index: 133

Text #17

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9473. Min Act: -0.1700

Data Index: 6714302 (Open Web Text)

Max Activating Token Index: 458

Text #18

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9452. Min Act: -0.1700

Data Index: 2555997 (Open Web Text)

Max Activating Token Index: 870

Text #19

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.9523. Min Act: -0.1700

Data Index: 1687240 (Open Web Text)

Max Activating Token Index: 553