Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.3485. Min Act: -0.1699
Data Index: 2065531 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.3171. Min Act: -0.1700
Data Index: 485000 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.3485. Min Act: -0.1700
Data Index: 5555599 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.2543. Min Act: -0.1690
Data Index: 318841 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.2228. Min Act: -0.1700
Data Index: 6903767 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.2228. Min Act: -0.1699
Data Index: 4821412 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.2228. Min Act: -0.1700
Data Index: 2914386 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.1914. Min Act: -0.1700
Data Index: 1969607 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.1442. Min Act: -0.1696
Data Index: 1343911 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.1127. Min Act: -0.1700
Data Index: 4325660 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0969. Min Act: -0.1700
Data Index: 3893753 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0969. Min Act: -0.1700
Data Index: 1905382 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0812. Min Act: -0.1700
Data Index: 5939435 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0969. Min Act: -0.1700
Data Index: 5952772 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0812. Min Act: -0.1700
Data Index: 4450019 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0812. Min Act: -0.1700
Data Index: 32682 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0654. Min Act: -0.1700
Data Index: 8287892 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0496. Min Act: -0.1700
Data Index: 357977 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0338. Min Act: -0.1699
Data Index: 6882722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3485. Min Range: -3.3485
Max Act: 3.0338. Min Act: -0.1700
Data Index: 1047014 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19