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

Dataset: Open Web Text

Neuron 2228 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: 2.7026. Min Range: -2.7026

Max Act: 2.6975. Min Act: -0.1700

Data Index: 5587114 (Open Web Text)

Max Activating Token Index: 572

Text #1

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.7026. Min Act: -0.1700

Data Index: 4115638 (Open Web Text)

Max Activating Token Index: 78

Text #2

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6824. Min Act: -0.1700

Data Index: 7680471 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6700. Min Act: -0.1700

Data Index: 6791056 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6575. Min Act: -0.1700

Data Index: 4159082 (Open Web Text)

Max Activating Token Index: 523

Text #5

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6506. Min Act: -0.1700

Data Index: 1973513 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6520. Min Act: -0.1700

Data Index: 7175214 (Open Web Text)

Max Activating Token Index: 454

Text #7

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6344. Min Act: -0.1700

Data Index: 5948987 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6265. Min Act: -0.1700

Data Index: 5363067 (Open Web Text)

Max Activating Token Index: 610

Text #9

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6321. Min Act: -0.1700

Data Index: 4461133 (Open Web Text)

Max Activating Token Index: 830

Text #10

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6339. Min Act: -0.1700

Data Index: 2146996 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6291. Min Act: -0.1700

Data Index: 6339829 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6088. Min Act: -0.1700

Data Index: 4063120 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6084. Min Act: -0.1700

Data Index: 4175332 (Open Web Text)

Max Activating Token Index: 610

Text #14

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6145. Min Act: -0.1700

Data Index: 7417271 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6123. Min Act: -0.1700

Data Index: 6503649 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6219. Min Act: -0.1700

Data Index: 8025943 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6175. Min Act: -0.1700

Data Index: 1644859 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.6253. Min Act: -0.1700

Data Index: 2553862 (Open Web Text)

Max Activating Token Index: 850

Text #19

Max Range: 2.7026. Min Range: -2.7026

Max Act: 2.5917. Min Act: -0.1700

Data Index: 2264803 (Open Web Text)

Max Activating Token Index: 978