Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2150 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.7160. Min Act: -0.1700
Data Index: 8546140 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.6535. Min Act: -0.1700
Data Index: 748304 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.6848. Min Act: -0.1700
Data Index: 5462198 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.6535. Min Act: -0.1700
Data Index: 7372430 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.5285. Min Act: -0.1700
Data Index: 481410 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.4973. Min Act: -0.1700
Data Index: 547041 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.4973. Min Act: -0.1700
Data Index: 6931806 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.4660. Min Act: -0.1700
Data Index: 6872065 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.4973. Min Act: -0.1700
Data Index: 224497 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.4035. Min Act: -0.0941
Data Index: 6068422 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.3723. Min Act: -0.1699
Data Index: 4289067 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.3723. Min Act: -0.1700
Data Index: 7154196 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.3098. Min Act: -0.1700
Data Index: 3563447 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.3098. Min Act: -0.1700
Data Index: 1101550 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.3098. Min Act: -0.1700
Data Index: 6068437 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.3098. Min Act: -0.1700
Data Index: 748301 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.3098. Min Act: -0.1700
Data Index: 1298536 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.2785. Min Act: -0.1700
Data Index: 391697 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.3098. Min Act: 0.0619
Data Index: 1477593 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7160. Min Range: -7.7160
Max Act: 7.2785. Min Act: -0.1700
Data Index: 4935788 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19