Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 522 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0886. Min Act: -0.1700
Data Index: 3755941 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0886. Min Act: -0.1700
Data Index: 8726851 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0886. Min Act: -0.1700
Data Index: 705654 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0886. Min Act: -0.1700
Data Index: 3196832 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0719. Min Act: -0.1700
Data Index: 988594 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0719. Min Act: -0.1700
Data Index: 1280348 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0719. Min Act: -0.1700
Data Index: 8004401 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0719. Min Act: -0.1700
Data Index: 5324383 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0719. Min Act: -0.1700
Data Index: 1142141 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0466. Min Act: -0.1700
Data Index: 539392 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0551. Min Act: -0.1700
Data Index: 720910 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0466. Min Act: -0.1700
Data Index: 5855450 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0382. Min Act: -0.1700
Data Index: 6041587 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0382. Min Act: -0.1700
Data Index: 6503764 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0382. Min Act: -0.1700
Data Index: 7516400 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0382. Min Act: -0.1700
Data Index: 2115067 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0382. Min Act: -0.1700
Data Index: 667208 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0382. Min Act: -0.1700
Data Index: 757893 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0214. Min Act: -0.1700
Data Index: 415904 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0886. Min Range: -2.0886
Max Act: 2.0298. Min Act: -0.1700
Data Index: 2384653 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19