Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2095 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7063. Min Range: -7.7063
Max Act: 7.7063. Min Act: -0.1700
Data Index: 6769655 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7063. Min Range: -7.7063
Max Act: 7.5813. Min Act: -0.1700
Data Index: 212355 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7063. Min Range: -7.7063
Max Act: 7.2688. Min Act: -0.1700
Data Index: 6769652 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7063. Min Range: -7.7063
Max Act: 7.2688. Min Act: -0.1700
Data Index: 8542589 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7063. Min Range: -7.7063
Max Act: 7.0813. Min Act: -0.1700
Data Index: 4202931 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7063. Min Range: -7.7063
Max Act: 7.0500. Min Act: -0.1700
Data Index: 2419698 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7063. Min Range: -7.7063
Max Act: 7.0188. Min Act: -0.1700
Data Index: 6372648 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7063. Min Range: -7.7063
Max Act: 7.0188. Min Act: -0.1700
Data Index: 360787 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.9563. Min Act: -0.1700
Data Index: 1089184 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.9250. Min Act: -0.1700
Data Index: 7556556 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.9250. Min Act: -0.1700
Data Index: 8430161 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.9250. Min Act: -0.1700
Data Index: 73810 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.9250. Min Act: -0.1700
Data Index: 2510389 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.8938. Min Act: -0.1700
Data Index: 6769657 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.8938. Min Act: -0.1700
Data Index: 3163265 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.8938. Min Act: -0.1700
Data Index: 5746467 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.8625. Min Act: -0.1700
Data Index: 6475521 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.8313. Min Act: -0.1700
Data Index: 476654 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.8000. Min Act: -0.1700
Data Index: 8419026 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7063. Min Range: -7.7063
Max Act: 6.8313. Min Act: -0.1700
Data Index: 8313095 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19