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

Dataset: Open Web Text

Neuron 2052 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: 4.7852. Min Range: -4.7852

Max Act: 4.7852. Min Act: -0.1700

Data Index: 6979393 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7251. Min Act: -0.1700

Data Index: 3626932 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7259. Min Act: -0.1700

Data Index: 1358133 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6989. Min Act: -0.1700

Data Index: 773992 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7064. Min Act: -0.1700

Data Index: 6275266 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6838. Min Act: -0.1700

Data Index: 6274 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6505. Min Act: -0.1700

Data Index: 2324469 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6445. Min Act: -0.1700

Data Index: 6628831 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6339. Min Act: -0.1700

Data Index: 944904 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6355. Min Act: -0.1700

Data Index: 7337162 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6157. Min Act: -0.1700

Data Index: 8670453 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6029. Min Act: -0.1700

Data Index: 2726151 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6026. Min Act: -0.1700

Data Index: 890090 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5685. Min Act: -0.1700

Data Index: 6007691 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5789. Min Act: -0.1700

Data Index: 3072082 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5891. Min Act: -0.1700

Data Index: 1319279 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5632. Min Act: -0.1700

Data Index: 4535603 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5881. Min Act: -0.1700

Data Index: 3278359 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5641. Min Act: -0.1700

Data Index: 3424393 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5709. Min Act: -0.1700

Data Index: 1418665 (Open Web Text)

Max Activating Token Index: 5