Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2947. Min Range: -10.2947
Max Act: 10.2947. Min Act: -0.1700
Data Index: 2218990 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2947. Min Range: -10.2947
Max Act: 10.1072. Min Act: -0.1700
Data Index: 4889541 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2947. Min Range: -10.2947
Max Act: 10.1072. Min Act: -0.1700
Data Index: 3291008 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.8572. Min Act: -0.1700
Data Index: 1069068 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.7322. Min Act: -0.1700
Data Index: 2017671 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.7322. Min Act: -0.1700
Data Index: 7783685 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.7322. Min Act: -0.1700
Data Index: 5888532 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.7322. Min Act: -0.1700
Data Index: 8652832 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.6072. Min Act: -0.1700
Data Index: 733063 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.5447. Min Act: -0.1700
Data Index: 4641255 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.5447. Min Act: -0.1700
Data Index: 6996957 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.5447. Min Act: -0.1700
Data Index: 4348785 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.5447. Min Act: -0.1700
Data Index: 4839526 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.5447. Min Act: -0.1700
Data Index: 8032842 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.5447. Min Act: -0.1700
Data Index: 1256085 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.4822. Min Act: -0.1700
Data Index: 2204142 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.3572. Min Act: -0.1700
Data Index: 5943392 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.4197. Min Act: -0.1700
Data Index: 948845 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.4822. Min Act: -0.1700
Data Index: 924587 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2947. Min Range: -10.2947
Max Act: 9.3572. Min Act: -0.1700
Data Index: 6518152 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19