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

Dataset: Open Web Text

Neuron 2934 in Layer 4

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: 3.7908. Min Range: -3.7908

Max Act: 3.7908. Min Act: -0.1700

Data Index: 1928689 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6641. Min Act: -0.1700

Data Index: 1903559 (Open Web Text)

Max Activating Token Index: 1011

Text #2

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6776. Min Act: -0.1700

Data Index: 2562365 (Open Web Text)

Max Activating Token Index: 148

Text #3

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6199. Min Act: -0.1700

Data Index: 4599795 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5850. Min Act: -0.1700

Data Index: 4556956 (Open Web Text)

Max Activating Token Index: 957

Text #5

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5921. Min Act: -0.1700

Data Index: 1311460 (Open Web Text)

Max Activating Token Index: 647

Text #6

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.6014. Min Act: -0.1700

Data Index: 6427910 (Open Web Text)

Max Activating Token Index: 351

Text #7

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5540. Min Act: -0.1700

Data Index: 4113662 (Open Web Text)

Max Activating Token Index: 477

Text #8

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5674. Min Act: -0.1700

Data Index: 2389765 (Open Web Text)

Max Activating Token Index: 881

Text #9

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5764. Min Act: -0.1700

Data Index: 5443318 (Open Web Text)

Max Activating Token Index: 754

Text #10

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5625. Min Act: -0.1700

Data Index: 6835802 (Open Web Text)

Max Activating Token Index: 582

Text #11

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5486. Min Act: -0.1700

Data Index: 1498935 (Open Web Text)

Max Activating Token Index: 771

Text #12

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5287. Min Act: -0.1700

Data Index: 2997863 (Open Web Text)

Max Activating Token Index: 742

Text #13

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5226. Min Act: -0.1700

Data Index: 4453931 (Open Web Text)

Max Activating Token Index: 688

Text #14

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5026. Min Act: -0.1700

Data Index: 4747 (Open Web Text)

Max Activating Token Index: 668

Text #15

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5243. Min Act: -0.1700

Data Index: 8678894 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5164. Min Act: -0.1700

Data Index: 6617785 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5271. Min Act: -0.1700

Data Index: 6915289 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.5099. Min Act: -0.1700

Data Index: 198652 (Open Web Text)

Max Activating Token Index: 930

Text #19

Max Range: 3.7908. Min Range: -3.7908

Max Act: 3.4909. Min Act: -0.1700

Data Index: 2949960 (Open Web Text)

Max Activating Token Index: 575