Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 568 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.8306. Min Act: -0.1700
Data Index: 8418234 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.8306. Min Act: -0.1700
Data Index: 7399414 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.7681. Min Act: -0.1700
Data Index: 1558528 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.7056. Min Act: -0.1700
Data Index: 1118255 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5806. Min Act: -0.1700
Data Index: 3882548 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5806. Min Act: -0.1700
Data Index: 3709003 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5806. Min Act: -0.1700
Data Index: 2553542 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5806. Min Act: -0.1700
Data Index: 5871990 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.5181. Min Act: -0.1700
Data Index: 3898357 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.4556. Min Act: -0.1700
Data Index: 4765568 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.4556. Min Act: -0.1700
Data Index: 51651 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.4556. Min Act: -0.1700
Data Index: 2403495 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3306. Min Act: -0.1700
Data Index: 8409632 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.2681. Min Act: -0.1700
Data Index: 3012258 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3306. Min Act: -0.1700
Data Index: 4399061 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3306. Min Act: -0.1700
Data Index: 7732695 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3306. Min Act: -0.1700
Data Index: 1640103 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.3306. Min Act: -0.1700
Data Index: 5553275 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.2681. Min Act: -0.1700
Data Index: 7774466 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8306. Min Range: -8.8306
Max Act: 8.2681. Min Act: -0.1700
Data Index: 115711 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19