Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.5363. Min Act: -0.1700
Data Index: 5272289 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.5050. Min Act: -0.1700
Data Index: 6996232 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.5050. Min Act: -0.1700
Data Index: 623198 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.3800. Min Act: -0.1700
Data Index: 952270 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.2550. Min Act: -0.1700
Data Index: 1937112 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.1613. Min Act: -0.1700
Data Index: 6147543 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.1613. Min Act: -0.1700
Data Index: 94155 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.1613. Min Act: -0.1700
Data Index: 3837108 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.1613. Min Act: -0.1700
Data Index: 3910919 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.1300. Min Act: -0.1700
Data Index: 310404 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.1300. Min Act: -0.1700
Data Index: 704454 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.0988. Min Act: -0.1700
Data Index: 3163495 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.0988. Min Act: -0.1700
Data Index: 3225881 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.0675. Min Act: -0.1700
Data Index: 3871557 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.0675. Min Act: -0.1700
Data Index: 3181795 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.0675. Min Act: -0.1700
Data Index: 4413235 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.0675. Min Act: -0.1700
Data Index: 1711322 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.0988. Min Act: -0.1700
Data Index: 66223 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.0675. Min Act: -0.1700
Data Index: 6929488 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5363. Min Range: -5.5363
Max Act: 5.0363. Min Act: -0.1700
Data Index: 6200540 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19