Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3798. Min Range: -7.3798
Max Act: 7.3798. Min Act: -0.1700
Data Index: 5023685 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3798. Min Range: -7.3798
Max Act: 7.0360. Min Act: -0.1700
Data Index: 2943771 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3798. Min Range: -7.3798
Max Act: 7.0360. Min Act: -0.1700
Data Index: 2988738 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.9423. Min Act: -0.1700
Data Index: 5984194 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.9423. Min Act: -0.1700
Data Index: 1447993 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.8798. Min Act: -0.1700
Data Index: 2083398 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.8485. Min Act: -0.1700
Data Index: 8673027 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.8173. Min Act: -0.1700
Data Index: 3819755 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.8173. Min Act: -0.1700
Data Index: 80708 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.7860. Min Act: -0.1700
Data Index: 3141958 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.7860. Min Act: -0.1700
Data Index: 1483907 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.7235. Min Act: -0.1700
Data Index: 5643328 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.7548. Min Act: -0.1700
Data Index: 3101722 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.7235. Min Act: -0.1700
Data Index: 6670051 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.7235. Min Act: -0.1700
Data Index: 4293823 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.7235. Min Act: -0.1700
Data Index: 7237166 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.6923. Min Act: -0.1700
Data Index: 2323982 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.6923. Min Act: -0.1700
Data Index: 3523619 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.6923. Min Act: -0.1700
Data Index: 5558892 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3798. Min Range: -7.3798
Max Act: 6.6923. Min Act: -0.1700
Data Index: 2839208 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19