Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.8750. Min Act: -0.1700
Data Index: 2830396 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.6875. Min Act: -0.1700
Data Index: 2223671 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.5625. Min Act: -0.1700
Data Index: 567931 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.6250. Min Act: -0.1700
Data Index: 2914784 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.6250. Min Act: -0.1700
Data Index: 2742011 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.5625. Min Act: -0.1700
Data Index: 4576540 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.6250. Min Act: -0.1700
Data Index: 1294012 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.5000. Min Act: -0.1700
Data Index: 1693448 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.5000. Min Act: -0.1700
Data Index: 7727202 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.5625. Min Act: -0.1700
Data Index: 7589092 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.5625. Min Act: -0.1700
Data Index: 4858792 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.5000. Min Act: -0.1700
Data Index: 6687340 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.4375. Min Act: -0.1700
Data Index: 2455884 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.4375. Min Act: -0.1700
Data Index: 1631617 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.3750. Min Act: -0.1700
Data Index: 7453182 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.4375. Min Act: -0.1700
Data Index: 2440696 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.4375. Min Act: -0.1700
Data Index: 2223672 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.4375. Min Act: -0.1700
Data Index: 6746836 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.3750. Min Act: -0.1700
Data Index: 430290 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8750. Min Range: -8.8750
Max Act: 8.3750. Min Act: -0.1700
Data Index: 2584428 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19