Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4503 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2962. Min Range: -9.2962
Max Act: 9.2962. Min Act: -0.1700
Data Index: 2251300 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2962. Min Range: -9.2962
Max Act: 9.1712. Min Act: -0.1700
Data Index: 2668117 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2962. Min Range: -9.2962
Max Act: 9.1087. Min Act: -0.1700
Data Index: 6837946 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2962. Min Range: -9.2962
Max Act: 9.0462. Min Act: -0.1700
Data Index: 4859264 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2962. Min Range: -9.2962
Max Act: 9.0462. Min Act: -0.1700
Data Index: 7645753 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2962. Min Range: -9.2962
Max Act: 9.0462. Min Act: -0.1700
Data Index: 7035923 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2962. Min Range: -9.2962
Max Act: 9.0462. Min Act: -0.1700
Data Index: 5073862 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9837. Min Act: -0.1700
Data Index: 5714016 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9837. Min Act: -0.1700
Data Index: 4587712 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2962. Min Range: -9.2962
Max Act: 9.0462. Min Act: -0.1700
Data Index: 4288032 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9837. Min Act: -0.1700
Data Index: 7206055 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9837. Min Act: -0.1700
Data Index: 4250732 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9837. Min Act: -0.1700
Data Index: 2725134 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9837. Min Act: -0.1700
Data Index: 3566645 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9837. Min Act: -0.1700
Data Index: 4895310 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9212. Min Act: -0.1700
Data Index: 2823185 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9212. Min Act: -0.1700
Data Index: 3073253 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9212. Min Act: -0.1700
Data Index: 838843 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9212. Min Act: -0.1700
Data Index: 233146 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2962. Min Range: -9.2962
Max Act: 8.9212. Min Act: -0.1700
Data Index: 6727698 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19