Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4424 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0058. Min Range: -8.0058
Max Act: 8.0058. Min Act: -0.1700
Data Index: 7217436 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0058. Min Range: -8.0058
Max Act: 8.0058. Min Act: -0.1700
Data Index: 6648706 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.7558. Min Act: -0.1700
Data Index: 1885770 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.6933. Min Act: -0.1700
Data Index: 6766269 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.5683. Min Act: -0.1700
Data Index: 2707627 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.5683. Min Act: -0.1700
Data Index: 7115479 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.6308. Min Act: -0.1700
Data Index: 8658642 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.5370. Min Act: -0.1700
Data Index: 6947634 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.5058. Min Act: -0.1700
Data Index: 7975026 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.4745. Min Act: -0.1700
Data Index: 5664377 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.4745. Min Act: -0.1700
Data Index: 7373424 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.3808. Min Act: -0.1700
Data Index: 8738382 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.4120. Min Act: -0.1700
Data Index: 5092304 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.3808. Min Act: -0.1700
Data Index: 6947871 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.4120. Min Act: -0.1700
Data Index: 1763464 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.3495. Min Act: -0.1700
Data Index: 3455345 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.3495. Min Act: -0.1700
Data Index: 2984525 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.3495. Min Act: -0.1700
Data Index: 5564305 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.3183. Min Act: -0.1700
Data Index: 2982502 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.3183. Min Act: -0.1700
Data Index: 5308064 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19