Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 753 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0259. Min Range: -10.0259
Max Act: 10.0259. Min Act: -0.1700
Data Index: 760533 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.9634. Min Act: -0.1700
Data Index: 6514799 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.9634. Min Act: -0.1700
Data Index: 4423886 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.9009. Min Act: -0.1700
Data Index: 5657782 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.7759. Min Act: -0.1700
Data Index: 4977162 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.7134. Min Act: -0.1700
Data Index: 6288251 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.6509. Min Act: -0.1700
Data Index: 2612880 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.5884. Min Act: -0.1700
Data Index: 7324936 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.5884. Min Act: -0.1700
Data Index: 770324 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.5259. Min Act: -0.1700
Data Index: 7056519 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.4634. Min Act: -0.1700
Data Index: 3796758 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.4634. Min Act: -0.1700
Data Index: 4503721 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.3384. Min Act: -0.1700
Data Index: 4911997 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.4009. Min Act: -0.1700
Data Index: 3158520 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.4009. Min Act: -0.1700
Data Index: 5855890 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.4009. Min Act: -0.1700
Data Index: 6787476 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.4009. Min Act: -0.1700
Data Index: 8459600 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.3384. Min Act: -0.1700
Data Index: 5273479 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.3384. Min Act: -0.1700
Data Index: 439217 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0259. Min Range: -10.0259
Max Act: 9.3384. Min Act: -0.1700
Data Index: 2571593 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19