Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4406 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3926. Min Range: -8.3926
Max Act: 8.3926. Min Act: -0.1700
Data Index: 7774139 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3926. Min Range: -8.3926
Max Act: 8.2676. Min Act: -0.1700
Data Index: 1716397 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3926. Min Range: -8.3926
Max Act: 8.2676. Min Act: -0.1700
Data Index: 4136458 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3926. Min Range: -8.3926
Max Act: 8.1426. Min Act: -0.1700
Data Index: 1865546 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3926. Min Range: -8.3926
Max Act: 8.1426. Min Act: -0.1700
Data Index: 1659030 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3926. Min Range: -8.3926
Max Act: 8.2051. Min Act: -0.1700
Data Index: 5591101 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.9864. Min Act: -0.1700
Data Index: 7700189 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.9239. Min Act: -0.1700
Data Index: 6937343 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.8926. Min Act: -0.1700
Data Index: 1382912 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.8614. Min Act: -0.1700
Data Index: 4537477 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.7989. Min Act: -0.1700
Data Index: 3040959 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.7676. Min Act: -0.1700
Data Index: 8565380 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.7676. Min Act: -0.1700
Data Index: 636956 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.7051. Min Act: -0.1700
Data Index: 2021499 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.6739. Min Act: -0.1700
Data Index: 6035686 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.7051. Min Act: -0.1700
Data Index: 2436962 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.6426. Min Act: -0.1700
Data Index: 4741362 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.6426. Min Act: -0.1700
Data Index: 110930 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.6114. Min Act: -0.1700
Data Index: 3038352 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3926. Min Range: -8.3926
Max Act: 7.6114. Min Act: -0.1700
Data Index: 7815915 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19