Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4894 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1787. Min Range: -5.1787
Max Act: 5.1787. Min Act: -0.1700
Data Index: 273362 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1787. Min Range: -5.1787
Max Act: 5.1787. Min Act: -0.1700
Data Index: 478115 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1787. Min Range: -5.1787
Max Act: 5.0849. Min Act: -0.1700
Data Index: 6766120 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.8974. Min Act: -0.1700
Data Index: 5508677 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.8974. Min Act: -0.1700
Data Index: 273363 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.8349. Min Act: -0.1700
Data Index: 2454358 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7724. Min Act: -0.1700
Data Index: 4310667 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.8037. Min Act: -0.1700
Data Index: 513184 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7412. Min Act: -0.1700
Data Index: 6331545 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7412. Min Act: -0.1700
Data Index: 2519825 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7724. Min Act: -0.1700
Data Index: 3337673 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7412. Min Act: -0.1700
Data Index: 52448 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7099. Min Act: -0.1700
Data Index: 52453 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7099. Min Act: -0.1700
Data Index: 4028337 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7099. Min Act: -0.1700
Data Index: 2582304 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7099. Min Act: -0.1700
Data Index: 8336656 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7099. Min Act: -0.1700
Data Index: 1522673 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.7099. Min Act: -0.1700
Data Index: 1888709 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.6787. Min Act: -0.1700
Data Index: 5509678 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1787. Min Range: -5.1787
Max Act: 4.6787. Min Act: -0.1700
Data Index: 8287774 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19