Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3393. Min Range: -7.3393
Max Act: 7.3393. Min Act: -0.1700
Data Index: 3716705 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3393. Min Range: -7.3393
Max Act: 7.2768. Min Act: -0.1700
Data Index: 4163385 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3393. Min Range: -7.3393
Max Act: 7.2768. Min Act: -0.1700
Data Index: 2442366 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3393. Min Range: -7.3393
Max Act: 7.1206. Min Act: -0.1700
Data Index: 8796690 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3393. Min Range: -7.3393
Max Act: 7.0581. Min Act: -0.1700
Data Index: 6533058 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3393. Min Range: -7.3393
Max Act: 7.0893. Min Act: -0.1700
Data Index: 5549459 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.9643. Min Act: -0.1700
Data Index: 1499853 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.9331. Min Act: -0.1700
Data Index: 3902216 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.9018. Min Act: -0.1700
Data Index: 6850384 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.9331. Min Act: -0.1700
Data Index: 4837264 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.8393. Min Act: -0.1700
Data Index: 2242961 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.7768. Min Act: -0.1700
Data Index: 6444782 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.8081. Min Act: -0.1700
Data Index: 2997729 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.7143. Min Act: -0.1700
Data Index: 6676780 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.6518. Min Act: -0.1700
Data Index: 1431547 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.6518. Min Act: -0.1700
Data Index: 5598404 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.6206. Min Act: -0.1700
Data Index: 5546053 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.6206. Min Act: -0.1700
Data Index: 8205315 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.5893. Min Act: -0.1700
Data Index: 7964828 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3393. Min Range: -7.3393
Max Act: 6.5581. Min Act: -0.1700
Data Index: 5196799 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19