Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2076. Min Range: -9.2076
Max Act: 9.2076. Min Act: -0.1700
Data Index: 2330956 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2076. Min Range: -9.2076
Max Act: 9.1451. Min Act: -0.1700
Data Index: 7816934 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2076. Min Range: -9.2076
Max Act: 9.1451. Min Act: -0.1700
Data Index: 2225265 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2076. Min Range: -9.2076
Max Act: 9.0201. Min Act: -0.1700
Data Index: 8605376 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2076. Min Range: -9.2076
Max Act: 9.0201. Min Act: -0.1700
Data Index: 4259263 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.9576. Min Act: -0.1700
Data Index: 3039729 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.9576. Min Act: -0.1700
Data Index: 7087423 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.8326. Min Act: -0.1700
Data Index: 2579922 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.7701. Min Act: -0.1700
Data Index: 3489336 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.8326. Min Act: -0.1700
Data Index: 4503125 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.7701. Min Act: -0.1700
Data Index: 3225676 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.7076. Min Act: -0.1700
Data Index: 6364063 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.7076. Min Act: -0.1700
Data Index: 3589829 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.6451. Min Act: -0.1700
Data Index: 8033011 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.5826. Min Act: -0.1700
Data Index: 1135721 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.5826. Min Act: -0.1700
Data Index: 1350629 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.5826. Min Act: -0.1700
Data Index: 7410096 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.5826. Min Act: -0.1700
Data Index: 1444201 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.5201. Min Act: -0.1700
Data Index: 7959677 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2076. Min Range: -9.2076
Max Act: 8.5201. Min Act: -0.1700
Data Index: 7404271 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19