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

Dataset: Open Web Text

Neuron 2856 in Layer 3

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: 3.0378. Min Range: -3.0378

Max Act: 3.0274. Min Act: -0.1700

Data Index: 2962492 (Open Web Text)

Max Activating Token Index: 736

Text #1

Max Range: 3.0378. Min Range: -3.0378

Max Act: 3.0298. Min Act: -0.1700

Data Index: 5073666 (Open Web Text)

Max Activating Token Index: 310

Text #2

Max Range: 3.0378. Min Range: -3.0378

Max Act: 3.0314. Min Act: -0.1700

Data Index: 8563251 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.0378. Min Range: -3.0378

Max Act: 3.0378. Min Act: -0.1700

Data Index: 3988891 (Open Web Text)

Max Activating Token Index: 622

Text #4

Max Range: 3.0378. Min Range: -3.0378

Max Act: 3.0130. Min Act: -0.1700

Data Index: 1002813 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9937. Min Act: -0.1700

Data Index: 5315109 (Open Web Text)

Max Activating Token Index: 269

Text #6

Max Range: 3.0378. Min Range: -3.0378

Max Act: 3.0090. Min Act: -0.1700

Data Index: 1647351 (Open Web Text)

Max Activating Token Index: 704

Text #7

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9978. Min Act: -0.1700

Data Index: 681183 (Open Web Text)

Max Activating Token Index: 380

Text #8

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9918. Min Act: -0.1700

Data Index: 3836197 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9712. Min Act: -0.1700

Data Index: 6251067 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9872. Min Act: -0.1700

Data Index: 6048012 (Open Web Text)

Max Activating Token Index: 1000

Text #11

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9813. Min Act: -0.1700

Data Index: 348978 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9308. Min Act: -0.1700

Data Index: 6133224 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9176. Min Act: -0.1700

Data Index: 2530088 (Open Web Text)

Max Activating Token Index: 337

Text #14

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9164. Min Act: -0.1700

Data Index: 7229895 (Open Web Text)

Max Activating Token Index: 742

Text #15

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9122. Min Act: -0.1700

Data Index: 2164719 (Open Web Text)

Max Activating Token Index: 223

Text #16

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9321. Min Act: -0.1700

Data Index: 1837890 (Open Web Text)

Max Activating Token Index: 30

Text #17

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9008. Min Act: -0.1700

Data Index: 332634 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9047. Min Act: -0.1700

Data Index: 2092204 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 3.0378. Min Range: -3.0378

Max Act: 2.9063. Min Act: -0.1700

Data Index: 2263618 (Open Web Text)

Max Activating Token Index: 81