Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5413 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.8309. Min Act: -0.1700
Data Index: 7058818 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7059. Min Act: -0.1700
Data Index: 2207205 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6434. Min Act: -0.1700
Data Index: 6126571 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6122. Min Act: -0.1700
Data Index: 8039930 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6122. Min Act: -0.1700
Data Index: 844342 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5809. Min Act: -0.1700
Data Index: 6071889 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5809. Min Act: -0.1700
Data Index: 3482768 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5809. Min Act: -0.1700
Data Index: 4420377 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6122. Min Act: -0.1700
Data Index: 2263577 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5497. Min Act: -0.1700
Data Index: 533157 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5497. Min Act: -0.1700
Data Index: 5065472 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5497. Min Act: -0.1700
Data Index: 3736387 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5497. Min Act: -0.1700
Data Index: 3816703 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5184. Min Act: -0.1700
Data Index: 3954779 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5497. Min Act: -0.1700
Data Index: 6513706 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5184. Min Act: -0.1700
Data Index: 1136796 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.4872. Min Act: -0.1700
Data Index: 6985914 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5184. Min Act: -0.1700
Data Index: 805523 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.4559. Min Act: -0.1700
Data Index: 1805645 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.4559. Min Act: -0.1700
Data Index: 2538716 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19