Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3165 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.4344. Min Act: -0.1700
Data Index: 6862556 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.3094. Min Act: -0.1700
Data Index: 2975532 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.2781. Min Act: -0.1700
Data Index: 4921216 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1844. Min Act: -0.1700
Data Index: 8537887 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1531. Min Act: -0.1700
Data Index: 4759658 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1219. Min Act: -0.1700
Data Index: 4127044 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.0906. Min Act: -0.1700
Data Index: 8503870 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.0906. Min Act: -0.1700
Data Index: 1143366 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.0281. Min Act: -0.1700
Data Index: 6697039 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.0594. Min Act: -0.1700
Data Index: 2868387 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.0594. Min Act: -0.1700
Data Index: 3702013 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.0906. Min Act: -0.1700
Data Index: 5057121 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.0594. Min Act: -0.1700
Data Index: 4153985 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.0281. Min Act: -0.1700
Data Index: 1572601 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.0281. Min Act: -0.1700
Data Index: 5092206 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4344. Min Range: -6.4344
Max Act: 5.9656. Min Act: -0.1700
Data Index: 8122881 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4344. Min Range: -6.4344
Max Act: 5.9656. Min Act: -0.1700
Data Index: 491514 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4344. Min Range: -6.4344
Max Act: 5.9656. Min Act: -0.1700
Data Index: 707953 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4344. Min Range: -6.4344
Max Act: 5.9969. Min Act: -0.1700
Data Index: 114358 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4344. Min Range: -6.4344
Max Act: 5.9656. Min Act: -0.1700
Data Index: 2668607 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19