Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1126 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.8440. Min Act: -0.1700
Data Index: 8068738 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.7815. Min Act: -0.1700
Data Index: 5309619 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.7815. Min Act: -0.1700
Data Index: 1952380 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.7502. Min Act: -0.1700
Data Index: 402003 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.6565. Min Act: -0.1700
Data Index: 5096436 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.6252. Min Act: -0.1700
Data Index: 1046221 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.5940. Min Act: -0.1700
Data Index: 4472597 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.5315. Min Act: -0.1700
Data Index: 3390664 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.5315. Min Act: -0.1700
Data Index: 7352937 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.5315. Min Act: -0.1700
Data Index: 8028861 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.5002. Min Act: -0.1700
Data Index: 700336 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.5002. Min Act: -0.1700
Data Index: 1530932 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.4690. Min Act: -0.1700
Data Index: 7735336 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.4690. Min Act: -0.1700
Data Index: 8526758 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.4690. Min Act: -0.1700
Data Index: 2851192 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.4690. Min Act: -0.1700
Data Index: 8109041 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.4377. Min Act: -0.1700
Data Index: 500491 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.4377. Min Act: -0.1700
Data Index: 5060387 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.4377. Min Act: -0.1700
Data Index: 2289539 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8440. Min Range: -4.8440
Max Act: 4.4065. Min Act: -0.1700
Data Index: 5734168 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19