Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.5557. Min Act: -0.1700
Data Index: 4598385 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.4307. Min Act: -0.1700
Data Index: 782602 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.3682. Min Act: -0.1700
Data Index: 7731881 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.3682. Min Act: -0.1700
Data Index: 8305934 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.3682. Min Act: -0.1700
Data Index: 5286717 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.3370. Min Act: -0.1700
Data Index: 1240137 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.2432. Min Act: -0.1700
Data Index: 8071703 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.2432. Min Act: -0.1700
Data Index: 273803 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.2432. Min Act: -0.1700
Data Index: 921543 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.2432. Min Act: -0.1700
Data Index: 7867920 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.1807. Min Act: -0.1700
Data Index: 50761 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.1182. Min Act: -0.1700
Data Index: 1526081 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.0870. Min Act: -0.1700
Data Index: 8400217 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.0870. Min Act: -0.1700
Data Index: 6883806 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.0557. Min Act: -0.1700
Data Index: 719908 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.0245. Min Act: -0.1700
Data Index: 3862585 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.0245. Min Act: -0.1700
Data Index: 6903392 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5557. Min Range: -6.5557
Max Act: 6.0245. Min Act: -0.1700
Data Index: 6276195 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5557. Min Range: -6.5557
Max Act: 5.9932. Min Act: -0.1700
Data Index: 1130844 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5557. Min Range: -6.5557
Max Act: 5.9932. Min Act: -0.1700
Data Index: 4365597 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19