Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.9449. Min Act: -0.1700
Data Index: 529425 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.9136. Min Act: -0.1700
Data Index: 8543592 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.8198. Min Act: -0.1700
Data Index: 1950307 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.8511. Min Act: -0.1700
Data Index: 1274968 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.8511. Min Act: -0.1700
Data Index: 4678990 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.8198. Min Act: -0.1700
Data Index: 1176498 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7885. Min Act: -0.1700
Data Index: 7824365 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7260. Min Act: -0.1700
Data Index: 1770301 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7572. Min Act: -0.1700
Data Index: 3144717 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7572. Min Act: -0.1700
Data Index: 4790204 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7260. Min Act: -0.1700
Data Index: 6824368 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7260. Min Act: -0.1700
Data Index: 4618857 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.6947. Min Act: -0.1700
Data Index: 3825240 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7260. Min Act: -0.1700
Data Index: 5102968 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7260. Min Act: -0.1700
Data Index: 389035 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7260. Min Act: -0.1700
Data Index: 4612052 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7260. Min Act: -0.1700
Data Index: 7573345 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7260. Min Act: -0.1700
Data Index: 5180085 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.6947. Min Act: -0.1700
Data Index: 4490944 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9449. Min Range: -3.9449
Max Act: 3.7260. Min Act: -0.1700
Data Index: 5554126 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19