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

Dataset: Open Web Text

Neuron 3012 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: 3.9731. Min Range: -3.9731

Max Act: 3.9731. Min Act: -0.1700

Data Index: 5698098 (Open Web Text)

Max Activating Token Index: 883

Text #1

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9431. Min Act: -0.1700

Data Index: 3169322 (Open Web Text)

Max Activating Token Index: 880

Text #2

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9537. Min Act: -0.1700

Data Index: 6096303 (Open Web Text)

Max Activating Token Index: 500

Text #3

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9017. Min Act: -0.1700

Data Index: 5398058 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8960. Min Act: -0.1700

Data Index: 4480266 (Open Web Text)

Max Activating Token Index: 893

Text #5

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9551. Min Act: -0.1700

Data Index: 3511654 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9484. Min Act: -0.1700

Data Index: 3503569 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9686. Min Act: -0.1700

Data Index: 3348966 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9453. Min Act: -0.1700

Data Index: 6096294 (Open Web Text)

Max Activating Token Index: 961

Text #9

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9514. Min Act: -0.1700

Data Index: 6453623 (Open Web Text)

Max Activating Token Index: 930

Text #10

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9293. Min Act: -0.1700

Data Index: 3053180 (Open Web Text)

Max Activating Token Index: 846

Text #11

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9081. Min Act: -0.1700

Data Index: 3140518 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9191. Min Act: -0.1700

Data Index: 8604288 (Open Web Text)

Max Activating Token Index: 879

Text #13

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9459. Min Act: -0.1700

Data Index: 5031217 (Open Web Text)

Max Activating Token Index: 394

Text #14

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8335. Min Act: -0.1700

Data Index: 1727567 (Open Web Text)

Max Activating Token Index: 619

Text #15

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8853. Min Act: -0.1700

Data Index: 1799320 (Open Web Text)

Max Activating Token Index: 941

Text #16

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8436. Min Act: -0.1700

Data Index: 1213606 (Open Web Text)

Max Activating Token Index: 623

Text #17

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8670. Min Act: -0.1700

Data Index: 5390871 (Open Web Text)

Max Activating Token Index: 798

Text #18

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8979. Min Act: -0.1700

Data Index: 487781 (Open Web Text)

Max Activating Token Index: 326

Text #19

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8656. Min Act: -0.1700

Data Index: 409237 (Open Web Text)

Max Activating Token Index: 804