Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3688 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6318. Min Range: -8.6318
Max Act: 8.6318. Min Act: -0.1700
Data Index: 5814798 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6318. Min Range: -8.6318
Max Act: 8.2256. Min Act: -0.1700
Data Index: 7440682 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6318. Min Range: -8.6318
Max Act: 8.1631. Min Act: -0.1700
Data Index: 3530260 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6318. Min Range: -8.6318
Max Act: 8.1318. Min Act: -0.1700
Data Index: 3471731 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6318. Min Range: -8.6318
Max Act: 8.0381. Min Act: -0.1700
Data Index: 668789 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6318. Min Range: -8.6318
Max Act: 8.0068. Min Act: -0.1700
Data Index: 1744912 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.9443. Min Act: -0.1700
Data Index: 8218769 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.9443. Min Act: -0.1700
Data Index: 3200775 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.9443. Min Act: -0.1700
Data Index: 7333080 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.8818. Min Act: -0.1700
Data Index: 8168552 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.8818. Min Act: -0.1700
Data Index: 6565041 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.8506. Min Act: -0.1700
Data Index: 5256549 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.8506. Min Act: -0.1700
Data Index: 3935468 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.8193. Min Act: -0.1700
Data Index: 1240032 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.7568. Min Act: -0.1700
Data Index: 638918 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.7568. Min Act: -0.1700
Data Index: 3463501 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.7881. Min Act: -0.1700
Data Index: 7108962 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.7568. Min Act: -0.1700
Data Index: 4788517 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.7568. Min Act: -0.1700
Data Index: 4733918 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6318. Min Range: -8.6318
Max Act: 7.7568. Min Act: -0.1700
Data Index: 3312595 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19