Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1801. Min Range: -6.1801
Max Act: 6.1801. Min Act: -0.1700
Data Index: 4744594 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.9926. Min Act: -0.1700
Data Index: 2970355 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.9614. Min Act: -0.1700
Data Index: 1041461 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.9301. Min Act: -0.1700
Data Index: 8440994 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.8989. Min Act: -0.1700
Data Index: 2417788 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.8989. Min Act: -0.1700
Data Index: 1083698 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.8676. Min Act: -0.1700
Data Index: 3570080 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.8051. Min Act: -0.1700
Data Index: 5109737 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.8051. Min Act: -0.1700
Data Index: 4837165 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.8051. Min Act: -0.1700
Data Index: 5035857 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.7739. Min Act: -0.1700
Data Index: 4517431 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.7739. Min Act: -0.1700
Data Index: 2525219 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.7739. Min Act: -0.1700
Data Index: 5928724 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.7739. Min Act: -0.1700
Data Index: 4376894 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.7426. Min Act: -0.1700
Data Index: 2318060 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.7426. Min Act: -0.1700
Data Index: 1061913 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.7426. Min Act: -0.1700
Data Index: 5508703 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.7114. Min Act: -0.1700
Data Index: 6327517 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.6489. Min Act: -0.1700
Data Index: 1387219 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1801. Min Range: -6.1801
Max Act: 5.6801. Min Act: -0.1700
Data Index: 2772761 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19