Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 824 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.3611. Min Act: -0.1700
Data Index: 2502313 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.3299. Min Act: -0.1700
Data Index: 8257116 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.2986. Min Act: -0.1700
Data Index: 8237718 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.2986. Min Act: -0.1700
Data Index: 7093009 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.2674. Min Act: -0.1700
Data Index: 2646542 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.2361. Min Act: -0.1700
Data Index: 7666961 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.2361. Min Act: -0.1700
Data Index: 7461174 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.2361. Min Act: -0.1700
Data Index: 1880156 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.2049. Min Act: -0.1700
Data Index: 4641684 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.2361. Min Act: -0.1700
Data Index: 5543928 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.2049. Min Act: -0.1700
Data Index: 8547730 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.1736. Min Act: -0.1700
Data Index: 8114026 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.1736. Min Act: -0.1700
Data Index: 7839769 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.1424. Min Act: -0.1700
Data Index: 4640737 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.1424. Min Act: -0.1700
Data Index: 2141590 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.1424. Min Act: -0.1700
Data Index: 7105571 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.1424. Min Act: -0.1700
Data Index: 5365347 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.1424. Min Act: -0.1700
Data Index: 5371357 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.1111. Min Act: -0.1700
Data Index: 6141227 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3611. Min Range: -7.3611
Max Act: 7.1424. Min Act: -0.1700
Data Index: 4229688 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19