Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7874. Min Act: -0.1700
Data Index: 1532685 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7790. Min Act: -0.1700
Data Index: 6145053 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7293. Min Act: -0.1700
Data Index: 3219747 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7211. Min Act: -0.1700
Data Index: 1706007 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7129. Min Act: -0.1700
Data Index: 630579 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7211. Min Act: -0.1700
Data Index: 67457 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7129. Min Act: -0.1700
Data Index: 483769 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7129. Min Act: -0.1700
Data Index: 1630379 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6966. Min Act: -0.1700
Data Index: 461445 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7047. Min Act: -0.1700
Data Index: 5973793 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.7047. Min Act: -0.1700
Data Index: 1948327 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6884. Min Act: -0.1700
Data Index: 2806458 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6966. Min Act: -0.1700
Data Index: 5103492 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6884. Min Act: -0.1700
Data Index: 169180 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6722. Min Act: -0.1700
Data Index: 4669881 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6722. Min Act: -0.1700
Data Index: 4640219 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6641. Min Act: -0.1700
Data Index: 2056578 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6641. Min Act: -0.1700
Data Index: 500096 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6561. Min Act: -0.1700
Data Index: 7966166 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7874. Min Range: -0.7874
Max Act: 0.6400. Min Act: -0.1700
Data Index: 956128 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19