Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2953 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1128. Min Range: -7.1128
Max Act: 7.1128. Min Act: -0.1700
Data Index: 5341150 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1128. Min Range: -7.1128
Max Act: 7.0815. Min Act: -0.1700
Data Index: 7992423 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1128. Min Range: -7.1128
Max Act: 7.0815. Min Act: -0.1700
Data Index: 6736330 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1128. Min Range: -7.1128
Max Act: 7.0190. Min Act: -0.1700
Data Index: 7809789 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.8628. Min Act: -0.1700
Data Index: 5722545 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.8628. Min Act: -0.1700
Data Index: 2992848 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.8628. Min Act: -0.1700
Data Index: 5341148 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.8315. Min Act: -0.1700
Data Index: 1519831 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.8003. Min Act: -0.1700
Data Index: 1585726 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.8003. Min Act: -0.1700
Data Index: 8002702 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.7690. Min Act: -0.1700
Data Index: 1776748 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.8003. Min Act: -0.1700
Data Index: 2759883 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.7378. Min Act: -0.1700
Data Index: 5341149 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.7378. Min Act: -0.1700
Data Index: 5341151 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.7378. Min Act: -0.1700
Data Index: 8027069 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.6753. Min Act: -0.1700
Data Index: 1776749 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.7065. Min Act: -0.1700
Data Index: 6065060 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.6753. Min Act: -0.1700
Data Index: 3080109 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.6753. Min Act: -0.1700
Data Index: 7430537 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1128. Min Range: -7.1128
Max Act: 6.6440. Min Act: -0.1700
Data Index: 5244117 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19