Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 671 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.7804. Min Act: -0.1700
Data Index: 8622896 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.7179. Min Act: -0.1700
Data Index: 6492655 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.6867. Min Act: -0.1700
Data Index: 8206257 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.6242. Min Act: -0.1700
Data Index: 871744 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.6867. Min Act: -0.1700
Data Index: 6449559 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.6242. Min Act: -0.1700
Data Index: 4943752 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.5617. Min Act: -0.1700
Data Index: 5861057 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.5617. Min Act: -0.1700
Data Index: 3211199 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.5304. Min Act: -0.1700
Data Index: 5094255 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.4992. Min Act: -0.1700
Data Index: 3754834 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.5304. Min Act: -0.1700
Data Index: 8015163 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.5304. Min Act: -0.1700
Data Index: 604388 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.4054. Min Act: -0.1700
Data Index: 4405060 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.4992. Min Act: -0.1700
Data Index: 4183085 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.4367. Min Act: -0.1700
Data Index: 6306197 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.4679. Min Act: -0.1700
Data Index: 2437939 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.4054. Min Act: -0.1700
Data Index: 5027134 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.4367. Min Act: -0.1700
Data Index: 2023849 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.4054. Min Act: -0.1700
Data Index: 4643142 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7804. Min Range: -7.7804
Max Act: 7.3742. Min Act: -0.1700
Data Index: 3691775 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19