Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 362 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.9260. Min Act: -0.1700
Data Index: 1159575 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.8635. Min Act: -0.1700
Data Index: 6897573 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.8635. Min Act: -0.1700
Data Index: 2015527 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.7697. Min Act: -0.1700
Data Index: 4474186 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.7385. Min Act: -0.1700
Data Index: 6674814 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.7072. Min Act: -0.1700
Data Index: 1664509 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.7072. Min Act: -0.1700
Data Index: 8229779 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.6760. Min Act: -0.1700
Data Index: 5119063 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.6760. Min Act: -0.1700
Data Index: 7188564 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.6760. Min Act: -0.1700
Data Index: 3960151 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.6447. Min Act: -0.1700
Data Index: 6861135 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.6135. Min Act: -0.1700
Data Index: 7223335 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.6135. Min Act: -0.1700
Data Index: 4862160 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.6135. Min Act: -0.1700
Data Index: 6594203 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.5822. Min Act: -0.1700
Data Index: 6073356 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.5822. Min Act: -0.1700
Data Index: 4749885 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.6135. Min Act: -0.1700
Data Index: 6613676 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.5822. Min Act: -0.1700
Data Index: 8546447 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.5822. Min Act: -0.1700
Data Index: 2813642 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9260. Min Range: -5.9260
Max Act: 5.5510. Min Act: -0.1700
Data Index: 411264 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19