Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3091. Min Range: -6.3091
Max Act: 6.3091. Min Act: -0.1700
Data Index: 1394085 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3091. Min Range: -6.3091
Max Act: 6.2778. Min Act: -0.1700
Data Index: 3576460 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3091. Min Range: -6.3091
Max Act: 6.0278. Min Act: -0.1700
Data Index: 4514018 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.9653. Min Act: -0.1700
Data Index: 1351848 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.9028. Min Act: -0.1700
Data Index: 5900795 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.9341. Min Act: -0.1700
Data Index: 466481 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.8403. Min Act: -0.1700
Data Index: 328920 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.8091. Min Act: -0.1700
Data Index: 5675505 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.8091. Min Act: -0.1700
Data Index: 774843 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.8091. Min Act: -0.1700
Data Index: 4135041 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.7778. Min Act: -0.1700
Data Index: 1805960 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.7466. Min Act: -0.1700
Data Index: 652371 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.6841. Min Act: -0.1700
Data Index: 5704889 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.6841. Min Act: -0.1700
Data Index: 5217374 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.6841. Min Act: -0.1700
Data Index: 1552820 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.6841. Min Act: -0.1700
Data Index: 6160511 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.6841. Min Act: -0.1700
Data Index: 4336870 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.6528. Min Act: -0.1700
Data Index: 2195045 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.6528. Min Act: -0.1700
Data Index: 131728 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3091. Min Range: -6.3091
Max Act: 5.6528. Min Act: -0.1700
Data Index: 5624848 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19