Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6386 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.8679. Min Act: -0.1700
Data Index: 1594468 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.6179. Min Act: -0.1700
Data Index: 561247 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.5554. Min Act: -0.1700
Data Index: 5182524 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.6179. Min Act: -0.1700
Data Index: 1007003 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.6179. Min Act: -0.1700
Data Index: 7719899 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.5554. Min Act: -0.1700
Data Index: 5271180 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.4929. Min Act: -0.1700
Data Index: 6237118 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.4929. Min Act: -0.1700
Data Index: 3883675 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.4929. Min Act: -0.1700
Data Index: 3635321 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.4304. Min Act: -0.1700
Data Index: 5001832 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.4304. Min Act: -0.1700
Data Index: 8164752 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.3991. Min Act: -0.1700
Data Index: 6173247 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.3991. Min Act: -0.1700
Data Index: 6556070 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.3991. Min Act: -0.1700
Data Index: 3873220 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.3366. Min Act: -0.1700
Data Index: 7146884 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.3679. Min Act: -0.1700
Data Index: 1857219 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.3054. Min Act: -0.1700
Data Index: 4670441 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.3366. Min Act: -0.1700
Data Index: 2285818 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.3366. Min Act: -0.1700
Data Index: 1561368 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8679. Min Range: -7.8679
Max Act: 7.3054. Min Act: -0.1700
Data Index: 1406798 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19