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

Dataset: Open Web Text

Neuron 1421 in Layer 0

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: 4.9647. Min Range: -4.9647

Max Act: 4.9647. Min Act: -0.1700

Data Index: 6073772 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8544. Min Act: -0.1700

Data Index: 6724708 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8683. Min Act: -0.1700

Data Index: 570180 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8562. Min Act: -0.1700

Data Index: 8426052 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8346. Min Act: -0.1700

Data Index: 6684162 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8372. Min Act: -0.1700

Data Index: 144092 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8231. Min Act: -0.1700

Data Index: 6222291 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8550. Min Act: -0.1700

Data Index: 8537806 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8426. Min Act: -0.1700

Data Index: 5352031 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8487. Min Act: -0.1700

Data Index: 7871083 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8395. Min Act: -0.1700

Data Index: 7217834 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8507. Min Act: -0.1700

Data Index: 7119007 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8362. Min Act: -0.1700

Data Index: 3676117 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8355. Min Act: -0.1700

Data Index: 6955803 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8273. Min Act: -0.1700

Data Index: 2899975 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8094. Min Act: -0.1700

Data Index: 5758478 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.7994. Min Act: -0.1700

Data Index: 6057014 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.7859. Min Act: -0.1700

Data Index: 2616202 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8040. Min Act: -0.1700

Data Index: 607791 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 4.9647. Min Range: -4.9647

Max Act: 4.8048. Min Act: -0.1700

Data Index: 6574876 (Open Web Text)

Max Activating Token Index: 8