Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.9116. Min Act: -0.1700
Data Index: 5375467 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.6616. Min Act: -0.1700
Data Index: 5127101 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.6304. Min Act: -0.1700
Data Index: 1702814 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.5991. Min Act: -0.1700
Data Index: 8684625 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.5679. Min Act: -0.1700
Data Index: 2234303 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.5366. Min Act: -0.1700
Data Index: 6475641 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.5679. Min Act: -0.1700
Data Index: 1980094 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.5366. Min Act: -0.1700
Data Index: 3132630 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.5366. Min Act: -0.1700
Data Index: 2932958 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.4741. Min Act: -0.1700
Data Index: 4991958 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.4741. Min Act: -0.1700
Data Index: 1736317 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.4741. Min Act: -0.1700
Data Index: 7289901 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.4116. Min Act: -0.1700
Data Index: 3290906 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.4116. Min Act: -0.1700
Data Index: 1238506 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.3804. Min Act: -0.1700
Data Index: 2602214 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.3804. Min Act: -0.1700
Data Index: 4751967 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.3804. Min Act: -0.1700
Data Index: 2440060 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.3804. Min Act: -0.1700
Data Index: 7522162 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.3804. Min Act: -0.1700
Data Index: 8398437 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9116. Min Range: -6.9116
Max Act: 6.3804. Min Act: -0.1700
Data Index: 3979481 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19