Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3929 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.7531. Min Act: -0.1700
Data Index: 8063575 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.6593. Min Act: -0.1700
Data Index: 8063579 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.5655. Min Act: -0.1700
Data Index: 4645844 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.5030. Min Act: -0.1700
Data Index: 4492514 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4405. Min Act: -0.1700
Data Index: 55631 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4093. Min Act: -0.1700
Data Index: 5468494 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4405. Min Act: -0.1700
Data Index: 414266 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4718. Min Act: -0.1700
Data Index: 6980106 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4405. Min Act: -0.1700
Data Index: 7792981 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4405. Min Act: -0.1700
Data Index: 8464895 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3780. Min Act: -0.1700
Data Index: 465164 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3780. Min Act: -0.1700
Data Index: 658297 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3468. Min Act: -0.1700
Data Index: 7055793 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3468. Min Act: -0.1700
Data Index: 8090633 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3468. Min Act: -0.1700
Data Index: 7705534 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3468. Min Act: -0.1700
Data Index: 7745804 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3468. Min Act: -0.1700
Data Index: 3628537 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3155. Min Act: -0.1700
Data Index: 2162037 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3155. Min Act: -0.1700
Data Index: 6584480 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.3155. Min Act: -0.1700
Data Index: 3687898 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19