Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2292 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1745. Min Range: -8.1745
Max Act: 8.1745. Min Act: -0.1700
Data Index: 3716105 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1745. Min Range: -8.1745
Max Act: 8.1120. Min Act: -0.1700
Data Index: 910220 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.9245. Min Act: -0.1700
Data Index: 3630128 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.6745. Min Act: -0.1700
Data Index: 4016399 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.6745. Min Act: -0.1700
Data Index: 8311403 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.6745. Min Act: -0.1700
Data Index: 7381702 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.6120. Min Act: -0.1700
Data Index: 3267337 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.5807. Min Act: -0.1700
Data Index: 3552978 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.5807. Min Act: -0.1700
Data Index: 894416 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.5807. Min Act: -0.1700
Data Index: 1721326 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.5182. Min Act: -0.1700
Data Index: 3849371 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.5182. Min Act: -0.1700
Data Index: 5231741 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.4870. Min Act: -0.1700
Data Index: 7833627 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.4870. Min Act: -0.1700
Data Index: 4497488 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.4870. Min Act: -0.1700
Data Index: 5684374 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.4870. Min Act: -0.1700
Data Index: 8565477 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.4870. Min Act: -0.1700
Data Index: 2494965 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.4870. Min Act: -0.1700
Data Index: 797041 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.4557. Min Act: -0.1700
Data Index: 6828299 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1745. Min Range: -8.1745
Max Act: 7.4557. Min Act: -0.1700
Data Index: 1385210 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19