Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9341. Min Range: -5.9341
Max Act: 5.9341. Min Act: -0.1700
Data Index: 4967484 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9341. Min Range: -5.9341
Max Act: 5.6216. Min Act: -0.1700
Data Index: 5717986 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9341. Min Range: -5.9341
Max Act: 5.5591. Min Act: -0.1700
Data Index: 4967465 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9341. Min Range: -5.9341
Max Act: 5.0591. Min Act: -0.1700
Data Index: 4672291 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9341. Min Range: -5.9341
Max Act: 5.0279. Min Act: -0.1700
Data Index: 935265 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9966. Min Act: -0.1700
Data Index: 7196066 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9966. Min Act: -0.1700
Data Index: 6056903 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9029. Min Act: -0.1700
Data Index: 856237 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9029. Min Act: -0.1700
Data Index: 856238 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9029. Min Act: -0.1700
Data Index: 8689961 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9029. Min Act: -0.1700
Data Index: 4967485 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9029. Min Act: -0.1700
Data Index: 6747851 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9029. Min Act: -0.1700
Data Index: 6978080 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9029. Min Act: -0.1700
Data Index: 8198107 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.9029. Min Act: -0.1700
Data Index: 2428131 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.8404. Min Act: -0.1700
Data Index: 6123705 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.8716. Min Act: -0.1700
Data Index: 7196067 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.8404. Min Act: -0.1700
Data Index: 3300319 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.8716. Min Act: -0.1700
Data Index: 4814083 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9341. Min Range: -5.9341
Max Act: 4.8404. Min Act: -0.1700
Data Index: 6592739 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19