Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1637. Min Range: -7.1637
Max Act: 7.1325. Min Act: -0.1700
Data Index: 5803040 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1637. Min Range: -7.1637
Max Act: 7.1637. Min Act: -0.1700
Data Index: 1996028 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1637. Min Range: -7.1637
Max Act: 7.1637. Min Act: -0.1700
Data Index: 5094731 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1637. Min Range: -7.1637
Max Act: 7.1012. Min Act: -0.1700
Data Index: 7219863 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1637. Min Range: -7.1637
Max Act: 7.1012. Min Act: -0.1700
Data Index: 7143780 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1637. Min Range: -7.1637
Max Act: 7.0700. Min Act: -0.1700
Data Index: 1434133 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1637. Min Range: -7.1637
Max Act: 7.0075. Min Act: -0.1700
Data Index: 468620 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1637. Min Range: -7.1637
Max Act: 7.0700. Min Act: -0.1700
Data Index: 841128 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.9762. Min Act: -0.1700
Data Index: 811642 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.9137. Min Act: -0.1700
Data Index: 366409 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.9137. Min Act: -0.1700
Data Index: 5616242 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.9137. Min Act: -0.1700
Data Index: 5940685 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.8825. Min Act: -0.1700
Data Index: 4583051 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.8512. Min Act: -0.1700
Data Index: 1433650 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.8512. Min Act: -0.1700
Data Index: 7654030 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.8512. Min Act: -0.1700
Data Index: 4332668 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.8512. Min Act: -0.1700
Data Index: 7999965 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.8200. Min Act: -0.1700
Data Index: 518722 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.7887. Min Act: -0.1700
Data Index: 8105760 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1637. Min Range: -7.1637
Max Act: 6.7887. Min Act: -0.1700
Data Index: 1807797 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19