Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4954 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7745. Min Range: -8.7745
Max Act: 8.7745. Min Act: -0.1658
Data Index: 3342696 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7745. Min Range: -8.7745
Max Act: 8.5870. Min Act: -0.1700
Data Index: 3318972 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7745. Min Range: -8.7745
Max Act: 8.2745. Min Act: -0.0292
Data Index: 2488008 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7745. Min Range: -8.7745
Max Act: 8.0245. Min Act: -0.1700
Data Index: 1027510 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.9620. Min Act: -0.1700
Data Index: 6943524 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.9620. Min Act: -0.1699
Data Index: 7277311 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.9620. Min Act: -0.1558
Data Index: 5834631 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.8995. Min Act: -0.1624
Data Index: 1524374 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.8995. Min Act: -0.1700
Data Index: 974667 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.8995. Min Act: -0.1699
Data Index: 8793156 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.8995. Min Act: -0.1605
Data Index: 2230551 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.8995. Min Act: -0.1700
Data Index: 2829210 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.8370. Min Act: -0.1700
Data Index: 664338 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.7745. Min Act: -0.1491
Data Index: 4468240 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.7120. Min Act: -0.1696
Data Index: 4671986 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.7120. Min Act: -0.1694
Data Index: 4502897 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.7120. Min Act: -0.1700
Data Index: 3829727 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.7120. Min Act: -0.1607
Data Index: 2680503 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.6495. Min Act: -0.1653
Data Index: 4671987 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7745. Min Range: -8.7745
Max Act: 7.6495. Min Act: -0.1700
Data Index: 2724574 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19