Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2497 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1438. Min Range: -7.1438
Max Act: 7.1438. Min Act: -0.1700
Data Index: 2935644 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1438. Min Range: -7.1438
Max Act: 7.1438. Min Act: -0.1700
Data Index: 6123764 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1438. Min Range: -7.1438
Max Act: 7.0188. Min Act: -0.1700
Data Index: 66713 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.9563. Min Act: -0.1700
Data Index: 5677516 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.9563. Min Act: -0.1700
Data Index: 2537481 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.9563. Min Act: -0.1700
Data Index: 4226660 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.8938. Min Act: -0.1700
Data Index: 5680333 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.9563. Min Act: -0.1700
Data Index: 2457564 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.8938. Min Act: -0.1700
Data Index: 6588925 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.8938. Min Act: -0.1700
Data Index: 8072506 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.8313. Min Act: -0.1700
Data Index: 8571619 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.8001. Min Act: -0.1700
Data Index: 2170314 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.8001. Min Act: -0.1700
Data Index: 8013389 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.7688. Min Act: -0.1700
Data Index: 7879808 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.7376. Min Act: -0.1700
Data Index: 7131204 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.7376. Min Act: -0.1700
Data Index: 7609977 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.7376. Min Act: -0.1700
Data Index: 8599391 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.7376. Min Act: -0.1700
Data Index: 3143495 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.7063. Min Act: -0.1700
Data Index: 783455 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1438. Min Range: -7.1438
Max Act: 6.7063. Min Act: -0.1700
Data Index: 94520 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19