Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2746. Min Range: -8.2746
Max Act: 8.2746. Min Act: -0.1700
Data Index: 6150477 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2746. Min Range: -8.2746
Max Act: 8.1808. Min Act: -0.1700
Data Index: 6150467 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.7433. Min Act: -0.1700
Data Index: 3950547 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.5871. Min Act: -0.1700
Data Index: 5363924 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.5246. Min Act: -0.1700
Data Index: 4410736 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.5558. Min Act: -0.1700
Data Index: 3901816 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.5558. Min Act: -0.1700
Data Index: 7787992 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.5558. Min Act: -0.1700
Data Index: 5200261 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.5558. Min Act: -0.1700
Data Index: 7282072 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.5558. Min Act: -0.1700
Data Index: 2631776 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.4621. Min Act: -0.1700
Data Index: 978596 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.5246. Min Act: -0.1700
Data Index: 1945581 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.4933. Min Act: -0.1700
Data Index: 4795574 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.4308. Min Act: -0.1700
Data Index: 363141 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.4308. Min Act: -0.1700
Data Index: 1113277 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.4308. Min Act: -0.1700
Data Index: 2998632 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.4621. Min Act: -0.1700
Data Index: 1710766 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.4308. Min Act: -0.1700
Data Index: 1956318 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.4308. Min Act: -0.1700
Data Index: 5082691 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2746. Min Range: -8.2746
Max Act: 7.4621. Min Act: -0.1700
Data Index: 4797218 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19