Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4504 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.2265. Min Act: -0.1700
Data Index: 2498830 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1640. Min Act: -0.1700
Data Index: 37951 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1327. Min Act: -0.1700
Data Index: 3920741 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1327. Min Act: -0.1700
Data Index: 4780596 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.0702. Min Act: -0.1700
Data Index: 3677481 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.0390. Min Act: -0.1700
Data Index: 6863828 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.9765. Min Act: -0.1700
Data Index: 2314416 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.9140. Min Act: -0.1700
Data Index: 5432962 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.9452. Min Act: -0.1700
Data Index: 1304012 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.9140. Min Act: -0.1700
Data Index: 432071 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.9140. Min Act: -0.1700
Data Index: 8580623 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.8827. Min Act: -0.1700
Data Index: 3949944 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.8515. Min Act: -0.1700
Data Index: 1229340 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.8515. Min Act: -0.1700
Data Index: 6171461 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.7890. Min Act: -0.1700
Data Index: 4139482 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.7890. Min Act: -0.1700
Data Index: 7068132 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.7890. Min Act: -0.1700
Data Index: 1428794 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.7265. Min Act: -0.1700
Data Index: 769467 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.7265. Min Act: -0.1700
Data Index: 1756905 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2265. Min Range: -5.2265
Max Act: 4.7265. Min Act: -0.1700
Data Index: 7729713 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19