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

Dataset: Open Web Text

Neuron 2459 in Layer 2

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: 5.3866. Min Range: -5.3866

Max Act: 5.3866. Min Act: -0.1700

Data Index: 1350389 (Open Web Text)

Max Activating Token Index: 618

Text #1

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.3209. Min Act: -0.1700

Data Index: 1280042 (Open Web Text)

Max Activating Token Index: 510

Text #2

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.2640. Min Act: -0.1700

Data Index: 1075415 (Open Web Text)

Max Activating Token Index: 341

Text #3

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.2055. Min Act: -0.1700

Data Index: 1280041 (Open Web Text)

Max Activating Token Index: 828

Text #4

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.2216. Min Act: -0.1700

Data Index: 6878676 (Open Web Text)

Max Activating Token Index: 675

Text #5

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.2197. Min Act: -0.1700

Data Index: 6694006 (Open Web Text)

Max Activating Token Index: 698

Text #6

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1784. Min Act: -0.1700

Data Index: 5034614 (Open Web Text)

Max Activating Token Index: 145

Text #7

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1483. Min Act: -0.1700

Data Index: 1076877 (Open Web Text)

Max Activating Token Index: 844

Text #8

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1438. Min Act: -0.1700

Data Index: 8185169 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1833. Min Act: -0.1700

Data Index: 1137550 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1880. Min Act: -0.1700

Data Index: 2138769 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1417. Min Act: -0.1700

Data Index: 5858428 (Open Web Text)

Max Activating Token Index: 790

Text #12

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1611. Min Act: -0.1700

Data Index: 6891030 (Open Web Text)

Max Activating Token Index: 190

Text #13

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1403. Min Act: -0.1700

Data Index: 5082297 (Open Web Text)

Max Activating Token Index: 467

Text #14

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.0970. Min Act: -0.1700

Data Index: 2103591 (Open Web Text)

Max Activating Token Index: 297

Text #15

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1453. Min Act: -0.1700

Data Index: 5563632 (Open Web Text)

Max Activating Token Index: 256

Text #16

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1021. Min Act: -0.1700

Data Index: 1937416 (Open Web Text)

Max Activating Token Index: 631

Text #17

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1027. Min Act: -0.1700

Data Index: 1114672 (Open Web Text)

Max Activating Token Index: 434

Text #18

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1474. Min Act: -0.1700

Data Index: 5682485 (Open Web Text)

Max Activating Token Index: 243

Text #19

Max Range: 5.3866. Min Range: -5.3866

Max Act: 5.1271. Min Act: -0.1700

Data Index: 316249 (Open Web Text)

Max Activating Token Index: 464