Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1040. Min Range: -7.1040
Max Act: 7.1040. Min Act: -0.1700
Data Index: 473630 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1040. Min Range: -7.1040
Max Act: 7.0727. Min Act: -0.1700
Data Index: 3330641 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9790. Min Act: -0.1700
Data Index: 3796290 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9790. Min Act: -0.1700
Data Index: 1529135 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9790. Min Act: -0.1700
Data Index: 5305012 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9477. Min Act: -0.1700
Data Index: 8518884 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9165. Min Act: -0.1700
Data Index: 5996729 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9477. Min Act: -0.1700
Data Index: 1524842 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9790. Min Act: -0.1700
Data Index: 3541114 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9165. Min Act: -0.1700
Data Index: 4041961 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9477. Min Act: -0.1700
Data Index: 2857440 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.8852. Min Act: -0.1700
Data Index: 5478747 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9165. Min Act: -0.1700
Data Index: 4742869 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.8852. Min Act: -0.1700
Data Index: 7941405 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9165. Min Act: -0.1700
Data Index: 4427197 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9165. Min Act: -0.1700
Data Index: 2600263 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.8852. Min Act: -0.1700
Data Index: 4708847 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9165. Min Act: -0.1700
Data Index: 2310861 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.9165. Min Act: -0.1700
Data Index: 2863550 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1040. Min Range: -7.1040
Max Act: 6.8852. Min Act: -0.1700
Data Index: 2800175 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19