Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3110 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.8808. Min Act: -0.1700
Data Index: 2594778 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.5370. Min Act: -0.1700
Data Index: 2996937 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.4745. Min Act: -0.1700
Data Index: 7950726 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.3808. Min Act: -0.1700
Data Index: 8750443 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.3808. Min Act: -0.1700
Data Index: 8559409 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.3808. Min Act: -0.1700
Data Index: 8424060 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.3183. Min Act: -0.1700
Data Index: 2683877 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.3183. Min Act: -0.1700
Data Index: 6361600 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.3183. Min Act: -0.1700
Data Index: 2677975 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.3183. Min Act: -0.1700
Data Index: 2992197 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2870. Min Act: -0.1700
Data Index: 2677994 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2870. Min Act: -0.1700
Data Index: 840485 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2558. Min Act: -0.1700
Data Index: 245148 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2558. Min Act: -0.1700
Data Index: 3085134 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2558. Min Act: -0.1700
Data Index: 4179843 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2245. Min Act: -0.1700
Data Index: 1339916 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2245. Min Act: -0.1700
Data Index: 4792155 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2245. Min Act: -0.1700
Data Index: 3069005 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2245. Min Act: -0.1700
Data Index: 3068991 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8808. Min Range: -5.8808
Max Act: 5.2245. Min Act: -0.1700
Data Index: 2677995 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19