Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0079. Min Range: -7.0079
Max Act: 7.0079. Min Act: -0.1700
Data Index: 6787920 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.8829. Min Act: -0.1700
Data Index: 8514912 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.8517. Min Act: -0.1700
Data Index: 4596034 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.8204. Min Act: -0.1700
Data Index: 3163386 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.7579. Min Act: -0.1700
Data Index: 8799561 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.6954. Min Act: -0.1700
Data Index: 7667126 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.6642. Min Act: -0.1700
Data Index: 1049034 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.6017. Min Act: -0.1700
Data Index: 6740134 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.6017. Min Act: -0.1700
Data Index: 7542957 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.6017. Min Act: -0.1700
Data Index: 8239367 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.5392. Min Act: -0.1700
Data Index: 8333693 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.5704. Min Act: -0.1700
Data Index: 8290366 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.5704. Min Act: -0.1700
Data Index: 7498115 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.5392. Min Act: -0.1700
Data Index: 4608787 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.5079. Min Act: -0.1700
Data Index: 1464488 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.4767. Min Act: -0.1700
Data Index: 6913866 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.4767. Min Act: -0.1700
Data Index: 7264673 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.4454. Min Act: -0.1700
Data Index: 1385612 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.4454. Min Act: -0.1700
Data Index: 1825461 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0079. Min Range: -7.0079
Max Act: 6.4142. Min Act: -0.1700
Data Index: 5473005 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19