Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1252 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.5975. Min Act: -0.1700
Data Index: 8164585 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.4725. Min Act: -0.1700
Data Index: 8578244 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.3475. Min Act: -0.1700
Data Index: 65840 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.2850. Min Act: -0.1700
Data Index: 7819702 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.2850. Min Act: -0.1700
Data Index: 5984616 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.2850. Min Act: -0.1700
Data Index: 5784654 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.2850. Min Act: -0.1700
Data Index: 1966367 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.2225. Min Act: -0.1700
Data Index: 2948582 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.2225. Min Act: -0.1700
Data Index: 5260415 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.1600. Min Act: -0.1700
Data Index: 3713662 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.1600. Min Act: -0.1700
Data Index: 438149 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.1600. Min Act: -0.1700
Data Index: 6092448 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.0975. Min Act: -0.1700
Data Index: 1760382 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.0975. Min Act: -0.1700
Data Index: 4074048 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.0350. Min Act: -0.1700
Data Index: 3795759 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.0350. Min Act: -0.1700
Data Index: 4479168 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.0350. Min Act: -0.1700
Data Index: 4141131 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5975. Min Range: -8.5975
Max Act: 8.0350. Min Act: -0.1700
Data Index: 2125804 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5975. Min Range: -8.5975
Max Act: 7.9725. Min Act: -0.1700
Data Index: 6781758 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5975. Min Range: -8.5975
Max Act: 7.8475. Min Act: -0.1700
Data Index: 660898 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19