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

Dataset: Open Web Text

Neuron 2883 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: 5.2133. Min Range: -5.2133

Max Act: 5.2133. Min Act: -0.1700

Data Index: 7405757 (Open Web Text)

Max Activating Token Index: 739

Text #1

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.2021. Min Act: -0.1700

Data Index: 6345388 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.2028. Min Act: -0.1700

Data Index: 3330165 (Open Web Text)

Max Activating Token Index: 605

Text #3

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.2046. Min Act: -0.1700

Data Index: 4105185 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1413. Min Act: -0.1700

Data Index: 1800584 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1764. Min Act: -0.1700

Data Index: 6471101 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1685. Min Act: -0.1700

Data Index: 1429837 (Open Web Text)

Max Activating Token Index: 150

Text #7

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1337. Min Act: -0.1700

Data Index: 4214970 (Open Web Text)

Max Activating Token Index: 630

Text #8

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1480. Min Act: -0.1700

Data Index: 4807091 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.0989. Min Act: -0.1700

Data Index: 7027051 (Open Web Text)

Max Activating Token Index: 710

Text #10

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1041. Min Act: -0.1700

Data Index: 1501471 (Open Web Text)

Max Activating Token Index: 907

Text #11

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1251. Min Act: -0.1700

Data Index: 8651894 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1128. Min Act: -0.1700

Data Index: 8515829 (Open Web Text)

Max Activating Token Index: 386

Text #13

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1037. Min Act: -0.1700

Data Index: 2985589 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.1194. Min Act: -0.1700

Data Index: 2753276 (Open Web Text)

Max Activating Token Index: 744

Text #15

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1969119 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.0617. Min Act: -0.1700

Data Index: 6498186 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.0508. Min Act: -0.1700

Data Index: 6634767 (Open Web Text)

Max Activating Token Index: 886

Text #18

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.0942. Min Act: -0.1700

Data Index: 6755054 (Open Web Text)

Max Activating Token Index: 705

Text #19

Max Range: 5.2133. Min Range: -5.2133

Max Act: 5.0638. Min Act: -0.1700

Data Index: 6998519 (Open Web Text)

Max Activating Token Index: 822