Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2366 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0756. Min Range: -5.0756
Max Act: 5.0756. Min Act: -0.1700
Data Index: 2038607 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0756. Min Range: -5.0756
Max Act: 5.0756. Min Act: -0.1700
Data Index: 3649240 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0756. Min Range: -5.0756
Max Act: 5.0131. Min Act: -0.1700
Data Index: 8771293 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.9506. Min Act: -0.1700
Data Index: 6583218 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.9193. Min Act: -0.1700
Data Index: 2133047 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.9193. Min Act: -0.1700
Data Index: 4707659 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.9193. Min Act: -0.1700
Data Index: 468452 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.8881. Min Act: -0.1700
Data Index: 2596078 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.8568. Min Act: -0.1700
Data Index: 83422 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.8568. Min Act: -0.1700
Data Index: 2236845 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.8568. Min Act: -0.1700
Data Index: 4259584 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.8568. Min Act: -0.1700
Data Index: 4395581 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.8256. Min Act: -0.1700
Data Index: 3098242 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.7943. Min Act: -0.1700
Data Index: 8808498 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.7631. Min Act: -0.1700
Data Index: 5668856 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.7318. Min Act: -0.1700
Data Index: 5758 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.7006. Min Act: -0.1700
Data Index: 1809417 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.7006. Min Act: -0.1700
Data Index: 7341684 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.7006. Min Act: -0.1700
Data Index: 7909673 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0756. Min Range: -5.0756
Max Act: 4.7006. Min Act: -0.1700
Data Index: 5284841 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19