Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0443. Min Range: -6.0443
Max Act: 6.0443. Min Act: -0.1700
Data Index: 2198021 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.9818. Min Act: -0.1700
Data Index: 5943024 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.9818. Min Act: -0.1700
Data Index: 5723260 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.9505. Min Act: -0.1700
Data Index: 3631146 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.9193. Min Act: -0.1700
Data Index: 3800619 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.8880. Min Act: -0.1700
Data Index: 3529740 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.8255. Min Act: -0.1700
Data Index: 4252547 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.8255. Min Act: -0.1700
Data Index: 6401137 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.7630. Min Act: -0.1700
Data Index: 318750 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.7630. Min Act: -0.1700
Data Index: 551938 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.7318. Min Act: -0.1700
Data Index: 2926641 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.7630. Min Act: -0.1700
Data Index: 5244679 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.7318. Min Act: -0.1700
Data Index: 1803890 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.6693. Min Act: -0.1700
Data Index: 5900082 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.7005. Min Act: -0.1700
Data Index: 160012 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.7005. Min Act: -0.1700
Data Index: 3753448 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.6693. Min Act: -0.1700
Data Index: 7195039 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.6693. Min Act: -0.1700
Data Index: 5683164 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.6693. Min Act: -0.1700
Data Index: 4243854 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0443. Min Range: -6.0443
Max Act: 5.6693. Min Act: -0.1700
Data Index: 600691 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19