Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1039. Min Range: -7.1039
Max Act: 7.1039. Min Act: -0.1700
Data Index: 8467119 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1039. Min Range: -7.1039
Max Act: 7.0101. Min Act: -0.1700
Data Index: 3461131 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1039. Min Range: -7.1039
Max Act: 7.0101. Min Act: -0.1700
Data Index: 7210065 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.8851. Min Act: -0.1700
Data Index: 1091233 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.8539. Min Act: -0.1700
Data Index: 1480219 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.9164. Min Act: -0.1700
Data Index: 1822227 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.8539. Min Act: -0.1700
Data Index: 3175726 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.8226. Min Act: -0.1700
Data Index: 4610394 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.7601. Min Act: -0.1700
Data Index: 650674 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.7914. Min Act: -0.1700
Data Index: 7815087 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.7601. Min Act: -0.1700
Data Index: 1996173 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.7601. Min Act: -0.1700
Data Index: 6837180 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.6976. Min Act: -0.1700
Data Index: 1410202 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.7289. Min Act: -0.1700
Data Index: 3279666 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.7289. Min Act: -0.1700
Data Index: 8335122 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.6664. Min Act: -0.1700
Data Index: 511663 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.6976. Min Act: -0.1700
Data Index: 3772390 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.6976. Min Act: -0.1700
Data Index: 6097963 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.6976. Min Act: -0.1700
Data Index: 7408581 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1039. Min Range: -7.1039
Max Act: 6.6976. Min Act: -0.1700
Data Index: 2874001 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19