Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1950 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.2387. Min Act: -0.1700
Data Index: 6478018 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.2074. Min Act: -0.1700
Data Index: 5876160 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.2074. Min Act: -0.1700
Data Index: 4166515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 3352113 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 885992 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 6740204 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 5932743 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 5563487 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 4937436 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 4878116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 1199495 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 3106883 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 6750180 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 2923408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 2143484 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 1729399 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 1559160 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 253512 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 1352872 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.1449. Min Act: -0.1700
Data Index: 1277004 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19