Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1993 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.9810. Min Act: -0.1700
Data Index: 7032912 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.9810. Min Act: -0.1700
Data Index: 6510490 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.9185. Min Act: -0.1700
Data Index: 3953505 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.8560. Min Act: -0.1700
Data Index: 943539 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.7935. Min Act: -0.1700
Data Index: 8662891 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.6685. Min Act: -0.1700
Data Index: 7848701 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.5435. Min Act: -0.1700
Data Index: 8301153 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.5435. Min Act: -0.1700
Data Index: 3087572 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.4810. Min Act: -0.1700
Data Index: 1838986 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.4810. Min Act: -0.1700
Data Index: 4965061 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.4810. Min Act: -0.1700
Data Index: 8056805 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.3560. Min Act: -0.1700
Data Index: 6379967 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.4185. Min Act: -0.1700
Data Index: 6220888 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.4185. Min Act: -0.1700
Data Index: 8029759 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.3560. Min Act: -0.1700
Data Index: 4369210 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.3560. Min Act: -0.1700
Data Index: 5537692 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.4185. Min Act: -0.1694
Data Index: 5419688 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.3560. Min Act: -0.1700
Data Index: 3126466 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.3560. Min Act: -0.1700
Data Index: 8644395 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9810. Min Range: -8.9810
Max Act: 8.3560. Min Act: -0.1700
Data Index: 6765301 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19