Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4868 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.8662. Min Act: -0.1700
Data Index: 649262 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.8662. Min Act: -0.1700
Data Index: 7908357 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.8350. Min Act: -0.1700
Data Index: 6341666 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7725. Min Act: -0.1700
Data Index: 976918 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7725. Min Act: -0.1700
Data Index: 7315424 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7725. Min Act: -0.1700
Data Index: 4279988 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7412. Min Act: -0.1700
Data Index: 4415336 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7412. Min Act: -0.1700
Data Index: 3222556 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7412. Min Act: -0.1700
Data Index: 3371521 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7412. Min Act: -0.1700
Data Index: 3371533 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7100. Min Act: -0.1700
Data Index: 7558201 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7100. Min Act: -0.1700
Data Index: 3371522 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7100. Min Act: -0.1700
Data Index: 5504912 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7100. Min Act: -0.1700
Data Index: 5338843 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.7100. Min Act: -0.1700
Data Index: 2760426 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.6787. Min Act: -0.1700
Data Index: 7315422 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.6475. Min Act: -0.1700
Data Index: 1111285 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.6787. Min Act: -0.1700
Data Index: 6662110 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.6787. Min Act: -0.1700
Data Index: 3371527 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8662. Min Range: -5.8662
Max Act: 5.6475. Min Act: -0.1700
Data Index: 2716626 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19