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

Dataset: Open Web Text

Neuron 1769 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: 3.0229. Min Range: -3.0229

Max Act: 3.0229. Min Act: -0.1700

Data Index: 5850160 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.0229. Min Range: -3.0229

Max Act: 3.0000. Min Act: -0.1700

Data Index: 5099741 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9641. Min Act: -0.1700

Data Index: 7989011 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9550. Min Act: -0.1700

Data Index: 2878870 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9550. Min Act: -0.1700

Data Index: 609170 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9482. Min Act: -0.1700

Data Index: 6550750 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9550. Min Act: -0.1700

Data Index: 2036245 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9410. Min Act: -0.1700

Data Index: 263743 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9550. Min Act: -0.1700

Data Index: 1280705 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9548. Min Act: -0.1700

Data Index: 7771688 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9300. Min Act: -0.1700

Data Index: 1463648 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9300. Min Act: -0.1700

Data Index: 5439483 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9300. Min Act: -0.1700

Data Index: 7979689 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9300. Min Act: -0.1700

Data Index: 7425323 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9355. Min Act: -0.1700

Data Index: 626663 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9300. Min Act: -0.1700

Data Index: 6222376 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9152. Min Act: -0.1700

Data Index: 2820822 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8982. Min Act: -0.1700

Data Index: 3469820 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9064. Min Act: -0.1700

Data Index: 5247957 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9058. Min Act: -0.1700

Data Index: 5023932 (Open Web Text)

Max Activating Token Index: 3