Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3631. Min Range: -7.3631
Max Act: 7.3631. Min Act: -0.1700
Data Index: 4615239 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3631. Min Range: -7.3631
Max Act: 7.1443. Min Act: -0.1700
Data Index: 2867653 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3631. Min Range: -7.3631
Max Act: 7.0193. Min Act: -0.1700
Data Index: 1057085 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.9256. Min Act: -0.1700
Data Index: 1720242 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8631. Min Act: -0.1700
Data Index: 7515715 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8943. Min Act: -0.1700
Data Index: 7695751 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8943. Min Act: -0.1700
Data Index: 2775713 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8943. Min Act: -0.1700
Data Index: 8169786 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8318. Min Act: -0.1700
Data Index: 6276274 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8318. Min Act: -0.1700
Data Index: 1418079 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8006. Min Act: -0.1700
Data Index: 1889497 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8006. Min Act: -0.1700
Data Index: 6529952 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8006. Min Act: -0.1700
Data Index: 3575575 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.7693. Min Act: -0.1700
Data Index: 8602378 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.7381. Min Act: -0.1700
Data Index: 677041 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.7068. Min Act: -0.1700
Data Index: 2294581 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.6756. Min Act: -0.1700
Data Index: 6055255 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.6756. Min Act: -0.1700
Data Index: 8426648 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.6756. Min Act: -0.1700
Data Index: 4757262 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.6443. Min Act: -0.1700
Data Index: 6560785 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19