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

Dataset: Open Web Text

Neuron 459 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: 3.0087. Min Range: -3.0087

Max Act: 3.0087. Min Act: -0.1700

Data Index: 806339 (Open Web Text)

Max Activating Token Index: 759

Text #1

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9875. Min Act: -0.1700

Data Index: 2686524 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9966. Min Act: -0.1700

Data Index: 6070704 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9657. Min Act: -0.1700

Data Index: 1613916 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9799. Min Act: -0.1700

Data Index: 8354344 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9753. Min Act: -0.1700

Data Index: 5428535 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9778. Min Act: -0.1700

Data Index: 2775995 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9671. Min Act: -0.1700

Data Index: 5102780 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9530. Min Act: -0.1700

Data Index: 7993878 (Open Web Text)

Max Activating Token Index: 80

Text #9

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9447. Min Act: -0.1700

Data Index: 3322523 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9422. Min Act: -0.1700

Data Index: 2068503 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9175. Min Act: -0.1700

Data Index: 73063 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9275. Min Act: -0.1700

Data Index: 8374525 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9354. Min Act: -0.1700

Data Index: 3840155 (Open Web Text)

Max Activating Token Index: 194

Text #14

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9348. Min Act: -0.1700

Data Index: 4281484 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9188. Min Act: -0.1700

Data Index: 7323219 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9411. Min Act: -0.1700

Data Index: 2599800 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9266. Min Act: -0.1700

Data Index: 3187567 (Open Web Text)

Max Activating Token Index: 427

Text #18

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9217. Min Act: -0.1700

Data Index: 6628971 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.9174. Min Act: -0.1700

Data Index: 69754 (Open Web Text)

Max Activating Token Index: 4