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

Dataset: Open Web Text

Neuron 980 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: 5.3544. Min Range: -5.3544

Max Act: 5.3544. Min Act: -0.1700

Data Index: 5477253 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2666. Min Act: -0.1700

Data Index: 833634 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1442. Min Act: -0.1700

Data Index: 6040154 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1279. Min Act: -0.1696

Data Index: 6060970 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1124. Min Act: -0.1700

Data Index: 8475736 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1139. Min Act: -0.1700

Data Index: 871884 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.0919. Min Act: -0.1700

Data Index: 6211032 (Open Web Text)

Max Activating Token Index: 300

Text #7

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.0798. Min Act: -0.1700

Data Index: 1574464 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1106. Min Act: -0.1700

Data Index: 5303426 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.0456. Min Act: -0.1700

Data Index: 8465196 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.0271. Min Act: -0.1700

Data Index: 5618460 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.0004. Min Act: -0.1700

Data Index: 4572586 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.3544. Min Range: -5.3544

Max Act: 4.9909. Min Act: -0.1700

Data Index: 1072097 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.0093. Min Act: -0.1700

Data Index: 5762589 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.3544. Min Range: -5.3544

Max Act: 4.9580. Min Act: -0.1700

Data Index: 4491090 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 5.3544. Min Range: -5.3544

Max Act: 4.9651. Min Act: -0.1700

Data Index: 1928099 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.3544. Min Range: -5.3544

Max Act: 4.9976. Min Act: -0.1700

Data Index: 5807386 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 5.3544. Min Range: -5.3544

Max Act: 4.9693. Min Act: -0.1700

Data Index: 1993118 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 5.3544. Min Range: -5.3544

Max Act: 4.9637. Min Act: -0.1699

Data Index: 1201477 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.3544. Min Range: -5.3544

Max Act: 4.9712. Min Act: -0.1700

Data Index: 5697488 (Open Web Text)

Max Activating Token Index: 6