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

Dataset: Open Web Text

Neuron 1596 in Layer 5

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: 3.5893. Min Range: -3.5893

Max Act: 3.5893. Min Act: -0.1700

Data Index: 887219 (Open Web Text)

Max Activating Token Index: 1004

Text #1

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.5846. Min Act: -0.1700

Data Index: 8364130 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.5439. Min Act: -0.1700

Data Index: 1101154 (Open Web Text)

Max Activating Token Index: 49

Text #3

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.5083. Min Act: -0.1700

Data Index: 1379604 (Open Web Text)

Max Activating Token Index: 1001

Text #4

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.5268. Min Act: -0.1700

Data Index: 7561792 (Open Web Text)

Max Activating Token Index: 972

Text #5

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.5095. Min Act: -0.1700

Data Index: 1331801 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.5087. Min Act: -0.1700

Data Index: 8008556 (Open Web Text)

Max Activating Token Index: 623

Text #7

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.5048. Min Act: -0.1700

Data Index: 4257839 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.5009. Min Act: -0.1700

Data Index: 2223046 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4960. Min Act: -0.1700

Data Index: 2496000 (Open Web Text)

Max Activating Token Index: 759

Text #10

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4874. Min Act: -0.1700

Data Index: 3895628 (Open Web Text)

Max Activating Token Index: 894

Text #11

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4959. Min Act: -0.1700

Data Index: 1630529 (Open Web Text)

Max Activating Token Index: 1004

Text #12

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4901. Min Act: -0.1700

Data Index: 7400862 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4721. Min Act: -0.1700

Data Index: 846509 (Open Web Text)

Max Activating Token Index: 352

Text #14

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4993. Min Act: -0.1700

Data Index: 6367191 (Open Web Text)

Max Activating Token Index: 391

Text #15

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4670. Min Act: -0.1700

Data Index: 1118403 (Open Web Text)

Max Activating Token Index: 480

Text #16

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4647. Min Act: -0.1700

Data Index: 6491480 (Open Web Text)

Max Activating Token Index: 166

Text #17

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4638. Min Act: -0.1700

Data Index: 2825507 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4542. Min Act: -0.1700

Data Index: 1730632 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 3.5893. Min Range: -3.5893

Max Act: 3.4449. Min Act: -0.1700

Data Index: 142013 (Open Web Text)

Max Activating Token Index: 957