Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2044 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0688. Min Range: -9.0688
Max Act: 9.0688. Min Act: -0.1700
Data Index: 4376795 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0688. Min Range: -9.0688
Max Act: 9.0063. Min Act: -0.1700
Data Index: 234726 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.8813. Min Act: -0.1700
Data Index: 2509056 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.8813. Min Act: -0.1700
Data Index: 2256885 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.8188. Min Act: -0.1700
Data Index: 5988085 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.8188. Min Act: -0.1700
Data Index: 6906555 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.7563. Min Act: -0.1700
Data Index: 1277446 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.7563. Min Act: -0.1700
Data Index: 132329 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6938. Min Act: -0.1700
Data Index: 1381703 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6938. Min Act: -0.1700
Data Index: 5696910 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6938. Min Act: -0.1700
Data Index: 7256769 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6938. Min Act: -0.1700
Data Index: 5423910 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6938. Min Act: -0.1700
Data Index: 2482693 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6313. Min Act: -0.1700
Data Index: 3835972 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6313. Min Act: -0.1700
Data Index: 6679568 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6313. Min Act: -0.1700
Data Index: 5129042 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6313. Min Act: -0.1700
Data Index: 7259952 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6313. Min Act: -0.1700
Data Index: 672176 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6313. Min Act: -0.1700
Data Index: 7381388 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0688. Min Range: -9.0688
Max Act: 8.6313. Min Act: -0.1700
Data Index: 7421888 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19