Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.4050. Min Act: -0.1700
Data Index: 3886129 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.3738. Min Act: -0.1700
Data Index: 4021151 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.3425. Min Act: -0.1700
Data Index: 8442068 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.3425. Min Act: -0.1700
Data Index: 7332665 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.3113. Min Act: -0.1700
Data Index: 4878502 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.3113. Min Act: -0.1700
Data Index: 11490 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.3113. Min Act: -0.1700
Data Index: 1442807 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.2488. Min Act: -0.1700
Data Index: 1145308 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.2800. Min Act: -0.1700
Data Index: 5930496 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.2800. Min Act: -0.1700
Data Index: 8058783 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.2488. Min Act: -0.1700
Data Index: 8230375 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.2175. Min Act: -0.1700
Data Index: 2582487 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.1863. Min Act: -0.1700
Data Index: 1950757 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.2175. Min Act: -0.1700
Data Index: 5924164 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.1863. Min Act: -0.1700
Data Index: 3435839 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.2175. Min Act: -0.1700
Data Index: 6456127 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.1863. Min Act: -0.1700
Data Index: 7765928 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.1863. Min Act: -0.1700
Data Index: 3754102 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.2175. Min Act: -0.1700
Data Index: 3837672 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4050. Min Range: -4.4050
Max Act: 4.1863. Min Act: -0.1700
Data Index: 139024 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19