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

Dataset: Open Web Text

Neuron 592 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: 1.9932. Min Range: -1.9932

Max Act: 1.9932. Min Act: -0.1700

Data Index: 3273358 (Open Web Text)

Max Activating Token Index: 409

Text #1

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.9478. Min Act: -0.1700

Data Index: 1268072 (Open Web Text)

Max Activating Token Index: 596

Text #2

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.9242. Min Act: -0.1700

Data Index: 2413414 (Open Web Text)

Max Activating Token Index: 303

Text #3

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.9328. Min Act: -0.1700

Data Index: 1706851 (Open Web Text)

Max Activating Token Index: 436

Text #4

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.9129. Min Act: -0.1700

Data Index: 618253 (Open Web Text)

Max Activating Token Index: 389

Text #5

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.9130. Min Act: -0.1700

Data Index: 2094434 (Open Web Text)

Max Activating Token Index: 157

Text #6

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.9040. Min Act: -0.1700

Data Index: 6077391 (Open Web Text)

Max Activating Token Index: 741

Text #7

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8997. Min Act: -0.1700

Data Index: 1014587 (Open Web Text)

Max Activating Token Index: 169

Text #8

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.9004. Min Act: -0.1700

Data Index: 1064411 (Open Web Text)

Max Activating Token Index: 789

Text #9

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.9056. Min Act: -0.1700

Data Index: 62891 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8844. Min Act: -0.1700

Data Index: 5191275 (Open Web Text)

Max Activating Token Index: 713

Text #11

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8869. Min Act: -0.1700

Data Index: 1282943 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8878. Min Act: -0.1700

Data Index: 2480011 (Open Web Text)

Max Activating Token Index: 62

Text #13

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8668. Min Act: -0.1700

Data Index: 3062524 (Open Web Text)

Max Activating Token Index: 568

Text #14

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8756. Min Act: -0.1700

Data Index: 8112920 (Open Web Text)

Max Activating Token Index: 832

Text #15

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8728. Min Act: -0.1700

Data Index: 528623 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8780. Min Act: -0.1700

Data Index: 7808073 (Open Web Text)

Max Activating Token Index: 311

Text #17

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8707. Min Act: -0.1700

Data Index: 8047275 (Open Web Text)

Max Activating Token Index: 572

Text #18

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8708. Min Act: -0.1700

Data Index: 350691 (Open Web Text)

Max Activating Token Index: 394

Text #19

Max Range: 1.9932. Min Range: -1.9932

Max Act: 1.8674. Min Act: -0.1700

Data Index: 2689166 (Open Web Text)

Max Activating Token Index: 496