Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1599 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6775. Min Range: -6.6775
Max Act: 6.6775. Min Act: -0.1700
Data Index: 4688982 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6775. Min Range: -6.6775
Max Act: 6.2088. Min Act: -0.1700
Data Index: 1158175 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6775. Min Range: -6.6775
Max Act: 6.1775. Min Act: -0.1700
Data Index: 3419082 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6775. Min Range: -6.6775
Max Act: 6.1463. Min Act: -0.1700
Data Index: 8275442 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.9900. Min Act: -0.1700
Data Index: 8070564 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.9588. Min Act: -0.1700
Data Index: 4623068 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.9588. Min Act: -0.1700
Data Index: 2650122 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.8338. Min Act: -0.1700
Data Index: 1515281 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.8338. Min Act: -0.1700
Data Index: 265662 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.8338. Min Act: -0.1700
Data Index: 5987265 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.8025. Min Act: -0.1700
Data Index: 1974527 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.8025. Min Act: -0.1700
Data Index: 6965894 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.7713. Min Act: -0.1700
Data Index: 1256310 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.7400. Min Act: -0.1700
Data Index: 5984120 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.7088. Min Act: -0.1700
Data Index: 3838150 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.7088. Min Act: -0.1700
Data Index: 3478496 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.7400. Min Act: -0.1700
Data Index: 926089 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.7088. Min Act: -0.1700
Data Index: 5916079 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.6775. Min Act: -0.1700
Data Index: 2728365 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6775. Min Range: -6.6775
Max Act: 5.6775. Min Act: -0.1700
Data Index: 3265895 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19