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

Dataset: Open Web Text

Neuron 2718 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: 4.3259. Min Range: -4.3259

Max Act: 4.3259. Min Act: -0.1700

Data Index: 5787618 (Open Web Text)

Max Activating Token Index: 24

Text #1

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.2604. Min Act: -0.1700

Data Index: 7034753 (Open Web Text)

Max Activating Token Index: 574

Text #2

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.2042. Min Act: -0.1700

Data Index: 1075428 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1916. Min Act: -0.1700

Data Index: 6896735 (Open Web Text)

Max Activating Token Index: 1005

Text #4

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1608. Min Act: -0.1700

Data Index: 2005519 (Open Web Text)

Max Activating Token Index: 171

Text #5

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1778. Min Act: -0.1700

Data Index: 4041867 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1601. Min Act: -0.1700

Data Index: 3113079 (Open Web Text)

Max Activating Token Index: 450

Text #7

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1669. Min Act: -0.1700

Data Index: 970086 (Open Web Text)

Max Activating Token Index: 810

Text #8

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1544. Min Act: -0.1700

Data Index: 6752572 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1937. Min Act: -0.1700

Data Index: 86297 (Open Web Text)

Max Activating Token Index: 750

Text #10

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1752. Min Act: -0.1700

Data Index: 5010804 (Open Web Text)

Max Activating Token Index: 643

Text #11

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1841. Min Act: -0.1700

Data Index: 1730045 (Open Web Text)

Max Activating Token Index: 782

Text #12

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1589. Min Act: -0.1700

Data Index: 6813376 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1607. Min Act: -0.1700

Data Index: 1018083 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1415. Min Act: -0.1700

Data Index: 7354994 (Open Web Text)

Max Activating Token Index: 821

Text #15

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1650. Min Act: -0.1700

Data Index: 3120391 (Open Web Text)

Max Activating Token Index: 584

Text #16

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1378. Min Act: -0.1700

Data Index: 7580218 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1610. Min Act: -0.1700

Data Index: 3764787 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1535. Min Act: -0.1700

Data Index: 4992413 (Open Web Text)

Max Activating Token Index: 435

Text #19

Max Range: 4.3259. Min Range: -4.3259

Max Act: 4.1095. Min Act: -0.1700

Data Index: 4015248 (Open Web Text)

Max Activating Token Index: 974