Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 25.9810. Min Range: -25.9810
Max Act: 25.9810. Min Act: -0.1700
Data Index: 7144009 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 25.9810. Min Range: -25.9810
Max Act: 24.4810. Min Act: -0.1700
Data Index: 2655328 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 25.9810. Min Range: -25.9810
Max Act: 23.7310. Min Act: -0.1700
Data Index: 5458639 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 25.9810. Min Range: -25.9810
Max Act: 23.3560. Min Act: -0.1700
Data Index: 4761337 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 25.9810. Min Range: -25.9810
Max Act: 23.2310. Min Act: -0.1700
Data Index: 2655327 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 25.9810. Min Range: -25.9810
Max Act: 23.2310. Min Act: -0.1700
Data Index: 3649072 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 25.9810. Min Range: -25.9810
Max Act: 23.1060. Min Act: -0.1700
Data Index: 8235750 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.7310. Min Act: -0.1700
Data Index: 3842708 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.9810. Min Act: -0.1700
Data Index: 2420309 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.8560. Min Act: -0.1700
Data Index: 2655329 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.8560. Min Act: -0.1700
Data Index: 8131152 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.7310. Min Act: -0.1700
Data Index: 3723458 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.8560. Min Act: -0.1700
Data Index: 7310259 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.7310. Min Act: -0.1700
Data Index: 5613624 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.6060. Min Act: -0.1700
Data Index: 5730910 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.6060. Min Act: -0.1700
Data Index: 189748 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.6060. Min Act: -0.1700
Data Index: 5253974 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.6060. Min Act: -0.1700
Data Index: 528594 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.4810. Min Act: -0.1700
Data Index: 5335239 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 25.9810. Min Range: -25.9810
Max Act: 22.4810. Min Act: -0.1700
Data Index: 5609948 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19