Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3754 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.7142. Min Act: -0.1700
Data Index: 7832001 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.6517. Min Act: -0.1700
Data Index: 1862422 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.6204. Min Act: -0.1700
Data Index: 1771845 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.5892. Min Act: -0.1700
Data Index: 8183152 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.4642. Min Act: -0.1700
Data Index: 7606762 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.3704. Min Act: -0.1700
Data Index: 4043560 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.3704. Min Act: -0.1700
Data Index: 6948687 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.2767. Min Act: -0.1700
Data Index: 5539520 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.2767. Min Act: -0.1700
Data Index: 5498496 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.2454. Min Act: -0.1700
Data Index: 5965926 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.2142. Min Act: -0.1700
Data Index: 5566781 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.2142. Min Act: -0.1700
Data Index: 4823631 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.1829. Min Act: -0.1700
Data Index: 557502 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.1517. Min Act: -0.1700
Data Index: 3430715 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.1517. Min Act: -0.1700
Data Index: 480715 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.1204. Min Act: -0.1699
Data Index: 2136586 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.0579. Min Act: -0.1700
Data Index: 7723102 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.0267. Min Act: -0.1700
Data Index: 6863032 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7142. Min Range: -7.7142
Max Act: 7.0579. Min Act: -0.1700
Data Index: 2931416 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7142. Min Range: -7.7142
Max Act: 6.9954. Min Act: -0.1700
Data Index: 2327652 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19