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

Dataset: Open Web Text

Neuron 1052 in Layer 4

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: 5.3384. Min Range: -5.3384

Max Act: 5.3384. Min Act: -0.1700

Data Index: 7752921 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.2888. Min Act: -0.1700

Data Index: 5188150 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.2754. Min Act: -0.1700

Data Index: 1159538 (Open Web Text)

Max Activating Token Index: 86

Text #3

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.2247. Min Act: -0.1700

Data Index: 1960997 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1912. Min Act: -0.1700

Data Index: 2744072 (Open Web Text)

Max Activating Token Index: 964

Text #5

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.2094. Min Act: -0.1700

Data Index: 7055928 (Open Web Text)

Max Activating Token Index: 63

Text #6

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1937. Min Act: -0.1700

Data Index: 8091085 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1821. Min Act: -0.1700

Data Index: 5156065 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.2104. Min Act: -0.1700

Data Index: 4470340 (Open Web Text)

Max Activating Token Index: 207

Text #9

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1893. Min Act: -0.1700

Data Index: 381713 (Open Web Text)

Max Activating Token Index: 170

Text #10

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1619. Min Act: -0.1700

Data Index: 4078477 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1667. Min Act: -0.1700

Data Index: 8383708 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1791. Min Act: -0.1700

Data Index: 8649487 (Open Web Text)

Max Activating Token Index: 100

Text #13

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1736. Min Act: -0.1700

Data Index: 4851608 (Open Web Text)

Max Activating Token Index: 202

Text #14

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1410. Min Act: -0.1700

Data Index: 8662577 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1411. Min Act: -0.1700

Data Index: 1758446 (Open Web Text)

Max Activating Token Index: 787

Text #16

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1433. Min Act: -0.1700

Data Index: 8509637 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1112. Min Act: -0.1700

Data Index: 685984 (Open Web Text)

Max Activating Token Index: 30

Text #18

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1705. Min Act: -0.1700

Data Index: 1793091 (Open Web Text)

Max Activating Token Index: 345

Text #19

Max Range: 5.3384. Min Range: -5.3384

Max Act: 5.1446. Min Act: -0.1700

Data Index: 2977062 (Open Web Text)

Max Activating Token Index: 46