Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 273 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1631. Min Range: -6.1631
Max Act: 6.1631. Min Act: -0.1700
Data Index: 8797806 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1631. Min Range: -6.1631
Max Act: 6.1006. Min Act: -0.1700
Data Index: 5023120 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1631. Min Range: -6.1631
Max Act: 6.0381. Min Act: -0.1700
Data Index: 6433984 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1631. Min Range: -6.1631
Max Act: 6.0068. Min Act: -0.1700
Data Index: 7553638 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.9756. Min Act: -0.1700
Data Index: 7138511 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.9443. Min Act: -0.1700
Data Index: 626533 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.9443. Min Act: -0.1700
Data Index: 6928586 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.9131. Min Act: -0.1700
Data Index: 2680870 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.9131. Min Act: -0.1700
Data Index: 3867272 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.9131. Min Act: -0.1700
Data Index: 1187082 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.9131. Min Act: -0.1700
Data Index: 227683 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.8818. Min Act: -0.1700
Data Index: 5570041 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.8506. Min Act: -0.1700
Data Index: 6716692 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.8818. Min Act: -0.1700
Data Index: 4696113 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.8818. Min Act: -0.1700
Data Index: 5951962 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.8818. Min Act: -0.1700
Data Index: 6790785 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.9131. Min Act: -0.1700
Data Index: 2633697 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.8506. Min Act: -0.1700
Data Index: 4440218 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.8506. Min Act: -0.1700
Data Index: 6239296 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1631. Min Range: -6.1631
Max Act: 5.8506. Min Act: -0.1700
Data Index: 820490 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19