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

Dataset: Open Web Text

Neuron 1499 in Layer 1

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: 1.6606. Min Range: -1.6606

Max Act: 1.6606. Min Act: -0.1700

Data Index: 7465018 (Open Web Text)

Max Activating Token Index: 509

Text #1

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.6248. Min Act: -0.1700

Data Index: 5824127 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.6295. Min Act: -0.1700

Data Index: 2788508 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.6131. Min Act: -0.1698

Data Index: 8125866 (Open Web Text)

Max Activating Token Index: 514

Text #4

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5968. Min Act: -0.1700

Data Index: 5600698 (Open Web Text)

Max Activating Token Index: 834

Text #5

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5857. Min Act: -0.1700

Data Index: 7214900 (Open Web Text)

Max Activating Token Index: 187

Text #6

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5834. Min Act: -0.1700

Data Index: 1689558 (Open Web Text)

Max Activating Token Index: 74

Text #7

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5729. Min Act: -0.1700

Data Index: 1072806 (Open Web Text)

Max Activating Token Index: 597

Text #8

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5625. Min Act: -0.1700

Data Index: 1322390 (Open Web Text)

Max Activating Token Index: 520

Text #9

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5656. Min Act: -0.1700

Data Index: 1392954 (Open Web Text)

Max Activating Token Index: 164

Text #10

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5715. Min Act: -0.1700

Data Index: 4073595 (Open Web Text)

Max Activating Token Index: 499

Text #11

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5577. Min Act: -0.1696

Data Index: 8181107 (Open Web Text)

Max Activating Token Index: 599

Text #12

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5563. Min Act: -0.1700

Data Index: 4105262 (Open Web Text)

Max Activating Token Index: 646

Text #13

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5560. Min Act: -0.1700

Data Index: 8342850 (Open Web Text)

Max Activating Token Index: 408

Text #14

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5485. Min Act: -0.1700

Data Index: 626484 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5446. Min Act: -0.1700

Data Index: 2695570 (Open Web Text)

Max Activating Token Index: 220

Text #16

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5425. Min Act: -0.1700

Data Index: 832264 (Open Web Text)

Max Activating Token Index: 99

Text #17

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5512. Min Act: -0.1700

Data Index: 3836851 (Open Web Text)

Max Activating Token Index: 703

Text #18

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5424. Min Act: -0.1700

Data Index: 7287526 (Open Web Text)

Max Activating Token Index: 900

Text #19

Max Range: 1.6606. Min Range: -1.6606

Max Act: 1.5326. Min Act: -0.1700

Data Index: 2564729 (Open Web Text)

Max Activating Token Index: 577