Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5251 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5807. Min Range: -7.5807
Max Act: 7.5807. Min Act: -0.1700
Data Index: 5089049 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5807. Min Range: -7.5807
Max Act: 7.5807. Min Act: -0.1700
Data Index: 3958549 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5807. Min Range: -7.5807
Max Act: 7.2994. Min Act: -0.1700
Data Index: 8342415 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5807. Min Range: -7.5807
Max Act: 7.1432. Min Act: -0.1700
Data Index: 6565920 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5807. Min Range: -7.5807
Max Act: 7.1432. Min Act: -0.1700
Data Index: 2310041 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5807. Min Range: -7.5807
Max Act: 7.0494. Min Act: -0.1700
Data Index: 5002796 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5807. Min Range: -7.5807
Max Act: 7.0182. Min Act: -0.1700
Data Index: 4026828 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5807. Min Range: -7.5807
Max Act: 7.0182. Min Act: -0.1700
Data Index: 2014634 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.9869. Min Act: -0.1700
Data Index: 5614588 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.9869. Min Act: -0.1700
Data Index: 8401302 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.9869. Min Act: -0.1700
Data Index: 6559096 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.9244. Min Act: -0.1700
Data Index: 1882045 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.8932. Min Act: -0.1700
Data Index: 3035169 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.8932. Min Act: -0.1700
Data Index: 3979704 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.8932. Min Act: -0.1700
Data Index: 336376 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.8932. Min Act: -0.1700
Data Index: 6902942 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.8619. Min Act: -0.1700
Data Index: 6800153 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.8307. Min Act: -0.1700
Data Index: 4993610 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.8619. Min Act: -0.1700
Data Index: 1059409 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5807. Min Range: -7.5807
Max Act: 6.7994. Min Act: -0.1700
Data Index: 5808620 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19