Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0516. Min Range: -7.0516
Max Act: 7.0516. Min Act: -0.1700
Data Index: 1985504 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.9891. Min Act: -0.1700
Data Index: 3056340 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.8953. Min Act: -0.1700
Data Index: 2175892 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.7703. Min Act: -0.1700
Data Index: 6308484 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.7391. Min Act: -0.1700
Data Index: 7044898 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.7078. Min Act: -0.1700
Data Index: 6165890 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.7078. Min Act: -0.1700
Data Index: 4261040 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.7078. Min Act: -0.1700
Data Index: 1393968 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.6766. Min Act: -0.1700
Data Index: 3904910 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.6453. Min Act: -0.1700
Data Index: 2792636 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.6453. Min Act: -0.1700
Data Index: 6050644 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.5828. Min Act: -0.1700
Data Index: 8692232 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.6453. Min Act: -0.1700
Data Index: 5394220 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.5828. Min Act: -0.1700
Data Index: 1459686 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.5828. Min Act: -0.1700
Data Index: 2652719 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.5516. Min Act: -0.1700
Data Index: 4458233 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.5828. Min Act: -0.1700
Data Index: 4609679 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.5516. Min Act: -0.1700
Data Index: 2948679 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.5516. Min Act: -0.1700
Data Index: 6055811 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0516. Min Range: -7.0516
Max Act: 6.5828. Min Act: -0.1700
Data Index: 4392074 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19