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

Dataset: Open Web Text

Neuron 1043 in Layer 6

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: 4.9823. Min Range: -4.9823

Max Act: 4.9823. Min Act: -0.1700

Data Index: 7170123 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.9505. Min Act: -0.1700

Data Index: 1145012 (Open Web Text)

Max Activating Token Index: 369

Text #2

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.9527. Min Act: -0.1700

Data Index: 5293652 (Open Web Text)

Max Activating Token Index: 847

Text #3

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.9452. Min Act: -0.1700

Data Index: 5646301 (Open Web Text)

Max Activating Token Index: 185

Text #4

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.8964. Min Act: -0.1700

Data Index: 1974618 (Open Web Text)

Max Activating Token Index: 510

Text #5

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.8028. Min Act: -0.1700

Data Index: 874990 (Open Web Text)

Max Activating Token Index: 297

Text #6

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.7677. Min Act: -0.1700

Data Index: 655986 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.7679. Min Act: -0.1700

Data Index: 5642345 (Open Web Text)

Max Activating Token Index: 378

Text #8

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.7070. Min Act: -0.1700

Data Index: 5851863 (Open Web Text)

Max Activating Token Index: 644

Text #9

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.7399. Min Act: -0.1700

Data Index: 5362371 (Open Web Text)

Max Activating Token Index: 1014

Text #10

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.7380. Min Act: -0.1700

Data Index: 3305756 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.6800. Min Act: -0.1700

Data Index: 5616043 (Open Web Text)

Max Activating Token Index: 379

Text #12

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.6902. Min Act: -0.1700

Data Index: 4957841 (Open Web Text)

Max Activating Token Index: 765

Text #13

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.6779. Min Act: -0.1700

Data Index: 8455270 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.7096. Min Act: -0.1700

Data Index: 4337740 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.6908. Min Act: -0.1700

Data Index: 4728042 (Open Web Text)

Max Activating Token Index: 972

Text #16

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.7074. Min Act: -0.1700

Data Index: 5441951 (Open Web Text)

Max Activating Token Index: 785

Text #17

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.7279. Min Act: -0.1700

Data Index: 802098 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.6878. Min Act: -0.1700

Data Index: 5105401 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 4.9823. Min Range: -4.9823

Max Act: 4.6703. Min Act: -0.1700

Data Index: 6267375 (Open Web Text)

Max Activating Token Index: 97