Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0324. Min Range: -8.0324
Max Act: 8.0324. Min Act: -0.1700
Data Index: 1186501 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0324. Min Range: -8.0324
Max Act: 8.0324. Min Act: -0.1700
Data Index: 6154930 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.9074. Min Act: -0.1700
Data Index: 3914440 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.9074. Min Act: -0.1700
Data Index: 451088 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.9074. Min Act: -0.1700
Data Index: 5913961 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.8449. Min Act: -0.1700
Data Index: 3123160 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.7824. Min Act: -0.1700
Data Index: 2467744 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.7824. Min Act: -0.1700
Data Index: 5702436 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.7199. Min Act: -0.1700
Data Index: 7332375 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.7824. Min Act: -0.1700
Data Index: 1093516 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.6887. Min Act: -0.1700
Data Index: 3748749 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.6887. Min Act: -0.1700
Data Index: 7342460 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.6262. Min Act: -0.1700
Data Index: 4157128 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.5949. Min Act: -0.1700
Data Index: 2175302 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.6262. Min Act: -0.1700
Data Index: 5723208 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.5637. Min Act: -0.1700
Data Index: 459564 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.5324. Min Act: -0.1700
Data Index: 5686859 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.5324. Min Act: -0.1700
Data Index: 5107145 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.5324. Min Act: -0.1700
Data Index: 2566354 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0324. Min Range: -8.0324
Max Act: 7.5324. Min Act: -0.1700
Data Index: 1361609 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19