Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.8117. Min Act: -0.1700
Data Index: 1497964 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.4679. Min Act: -0.1700
Data Index: 4961871 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.3117. Min Act: -0.1700
Data Index: 5891155 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.2804. Min Act: -0.1700
Data Index: 8716259 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.2179. Min Act: -0.1700
Data Index: 915072 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.2179. Min Act: -0.1700
Data Index: 5244562 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1554. Min Act: -0.1700
Data Index: 2388835 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1867. Min Act: -0.1700
Data Index: 5473606 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1554. Min Act: -0.1700
Data Index: 6981342 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1554. Min Act: -0.1700
Data Index: 4847593 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1554. Min Act: -0.1700
Data Index: 5557131 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1554. Min Act: -0.1700
Data Index: 2224583 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1242. Min Act: -0.1700
Data Index: 7333481 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1242. Min Act: -0.1700
Data Index: 5454788 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1242. Min Act: -0.1700
Data Index: 1983407 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1242. Min Act: -0.1700
Data Index: 354086 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1242. Min Act: -0.1700
Data Index: 6357047 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1242. Min Act: -0.1700
Data Index: 583936 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.1242. Min Act: -0.1700
Data Index: 6924356 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8117. Min Range: -6.8117
Max Act: 6.0929. Min Act: -0.1700
Data Index: 8657740 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19