Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6132 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3913. Min Range: -7.3913
Max Act: 7.3913. Min Act: -0.1700
Data Index: 3041425 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3913. Min Range: -7.3913
Max Act: 7.2975. Min Act: -0.1700
Data Index: 7001413 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3913. Min Range: -7.3913
Max Act: 7.1725. Min Act: -0.1700
Data Index: 5846587 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3913. Min Range: -7.3913
Max Act: 7.1100. Min Act: -0.1700
Data Index: 3987574 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.9225. Min Act: -0.1700
Data Index: 3520432 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.9225. Min Act: -0.1700
Data Index: 2167570 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.8913. Min Act: -0.1700
Data Index: 4890762 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.8600. Min Act: -0.1700
Data Index: 6756508 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.8600. Min Act: -0.1700
Data Index: 2761664 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.8913. Min Act: -0.1700
Data Index: 253155 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.8913. Min Act: -0.1700
Data Index: 2126854 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.7975. Min Act: -0.1700
Data Index: 3999642 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.7663. Min Act: -0.1700
Data Index: 3459020 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.7663. Min Act: -0.1700
Data Index: 5877436 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.7350. Min Act: -0.1700
Data Index: 4708065 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.6725. Min Act: -0.1700
Data Index: 3237408 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.6725. Min Act: -0.1700
Data Index: 7392343 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.6725. Min Act: -0.1700
Data Index: 7714238 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.6725. Min Act: -0.1700
Data Index: 8175691 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3913. Min Range: -7.3913
Max Act: 6.6413. Min Act: -0.1700
Data Index: 1213295 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19