Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.7666. Min Act: -0.1700
Data Index: 7772541 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6103. Min Act: -0.1700
Data Index: 8136652 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.5791. Min Act: -0.1700
Data Index: 499760 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.4853. Min Act: -0.1700
Data Index: 1017773 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.3603. Min Act: -0.1700
Data Index: 471148 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.3603. Min Act: -0.1700
Data Index: 4125939 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2978. Min Act: -0.1700
Data Index: 8013467 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.3291. Min Act: -0.1700
Data Index: 1059142 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.3291. Min Act: -0.1700
Data Index: 2016303 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.3291. Min Act: -0.1700
Data Index: 8457158 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.3291. Min Act: -0.1700
Data Index: 6955238 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2978. Min Act: -0.1700
Data Index: 5164572 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2978. Min Act: -0.1700
Data Index: 4323790 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2666. Min Act: -0.1700
Data Index: 8590453 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2666. Min Act: -0.1700
Data Index: 8474666 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2666. Min Act: -0.1700
Data Index: 6021241 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2666. Min Act: -0.1700
Data Index: 6026875 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2978. Min Act: -0.1700
Data Index: 1313505 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2666. Min Act: -0.1700
Data Index: 7849373 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.2041. Min Act: -0.1700
Data Index: 1364604 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19