Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4050. Min Range: -7.4050
Max Act: 7.4050. Min Act: -0.1700
Data Index: 478129 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4050. Min Range: -7.4050
Max Act: 7.3425. Min Act: -0.1700
Data Index: 6851750 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4050. Min Range: -7.4050
Max Act: 7.0925. Min Act: -0.1700
Data Index: 5390800 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4050. Min Range: -7.4050
Max Act: 7.0300. Min Act: -0.1700
Data Index: 3837090 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.9363. Min Act: -0.1700
Data Index: 7796613 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.9363. Min Act: -0.1700
Data Index: 5935629 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.9050. Min Act: -0.1700
Data Index: 6306450 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.9363. Min Act: -0.1700
Data Index: 2060241 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.8738. Min Act: -0.1700
Data Index: 5970299 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.8425. Min Act: -0.1700
Data Index: 6405002 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.8113. Min Act: -0.1700
Data Index: 4047554 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.8113. Min Act: -0.1700
Data Index: 2589013 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.7800. Min Act: -0.1700
Data Index: 4541217 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.8113. Min Act: -0.1700
Data Index: 8723780 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.7488. Min Act: -0.1700
Data Index: 4415658 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.7488. Min Act: -0.1700
Data Index: 4433200 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.7488. Min Act: -0.1700
Data Index: 6091213 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.7175. Min Act: -0.1700
Data Index: 6397928 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.7175. Min Act: -0.1700
Data Index: 1524887 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4050. Min Range: -7.4050
Max Act: 6.7175. Min Act: -0.1700
Data Index: 1242537 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19