Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 700 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.7913. Min Act: -0.1700
Data Index: 2724596 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.7288. Min Act: -0.1700
Data Index: 6659073 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.7288. Min Act: -0.1700
Data Index: 4007546 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.7288. Min Act: -0.1700
Data Index: 6423308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.6351. Min Act: -0.1700
Data Index: 2391182 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.6351. Min Act: -0.1700
Data Index: 8766112 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.6038. Min Act: -0.1700
Data Index: 5948261 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.5726. Min Act: -0.1700
Data Index: 7733043 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.5726. Min Act: -0.1700
Data Index: 4580151 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.5726. Min Act: -0.1700
Data Index: 2853779 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.5726. Min Act: -0.1700
Data Index: 5254987 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.5413. Min Act: -0.1700
Data Index: 1653640 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.5413. Min Act: -0.1700
Data Index: 6356956 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.5413. Min Act: -0.1700
Data Index: 7530758 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.4788. Min Act: -0.1700
Data Index: 2867414 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.5101. Min Act: -0.1700
Data Index: 4145165 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.4788. Min Act: -0.1700
Data Index: 7826322 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.4476. Min Act: -0.1700
Data Index: 5847245 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.4788. Min Act: -0.1700
Data Index: 7530889 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7913. Min Range: -6.7913
Max Act: 6.4476. Min Act: -0.1700
Data Index: 1080120 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19