Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.3807. Min Act: -0.1700
Data Index: 3554641 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.3807. Min Act: -0.1700
Data Index: 7986803 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.3182. Min Act: -0.1700
Data Index: 1445329 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.2557. Min Act: -0.1700
Data Index: 1934679 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.2557. Min Act: -0.1700
Data Index: 6540726 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.2557. Min Act: -0.1700
Data Index: 8626246 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.1307. Min Act: -0.1699
Data Index: 7055982 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.1307. Min Act: -0.1700
Data Index: 4675699 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.1307. Min Act: -0.1700
Data Index: 903271 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.0682. Min Act: -0.1700
Data Index: 8003558 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.0682. Min Act: -0.1700
Data Index: 1563018 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.0682. Min Act: -0.1700
Data Index: 2570782 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.0057. Min Act: -0.1700
Data Index: 3554343 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.0057. Min Act: -0.1700
Data Index: 6554384 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.0057. Min Act: -0.1700
Data Index: 2780750 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3807. Min Range: -10.3807
Max Act: 10.0057. Min Act: -0.1700
Data Index: 4668987 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3807. Min Range: -10.3807
Max Act: 9.9432. Min Act: -0.1700
Data Index: 1694500 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3807. Min Range: -10.3807
Max Act: 9.9432. Min Act: -0.1700
Data Index: 4045007 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3807. Min Range: -10.3807
Max Act: 9.8807. Min Act: -0.1700
Data Index: 7055983 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3807. Min Range: -10.3807
Max Act: 9.8807. Min Act: -0.1698
Data Index: 8172798 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19