Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0830. Min Range: -5.0830
Max Act: 5.0830. Min Act: -0.1700
Data Index: 3788129 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0830. Min Range: -5.0830
Max Act: 5.0205. Min Act: -0.1700
Data Index: 5879883 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.9580. Min Act: -0.1700
Data Index: 4483946 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.9580. Min Act: -0.1700
Data Index: 1059738 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.9267. Min Act: -0.1700
Data Index: 6674369 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.9267. Min Act: -0.1700
Data Index: 2212712 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.9267. Min Act: -0.1700
Data Index: 542163 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8955. Min Act: -0.1700
Data Index: 4990600 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8955. Min Act: -0.1700
Data Index: 6395506 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8955. Min Act: -0.1700
Data Index: 4098023 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8955. Min Act: -0.1700
Data Index: 3442152 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8642. Min Act: -0.1700
Data Index: 8399111 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8955. Min Act: -0.1700
Data Index: 2350867 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8330. Min Act: -0.1700
Data Index: 3541907 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8955. Min Act: -0.1700
Data Index: 8544710 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8642. Min Act: -0.1700
Data Index: 2358974 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8642. Min Act: -0.1700
Data Index: 7346886 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8642. Min Act: -0.1700
Data Index: 1412964 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8330. Min Act: -0.1700
Data Index: 5188301 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0830. Min Range: -5.0830
Max Act: 4.8330. Min Act: -0.1700
Data Index: 2566987 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19