Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4650 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9719. Min Act: -0.1700
Data Index: 1437110 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9719. Min Act: -0.1700
Data Index: 8474235 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9719. Min Act: -0.1700
Data Index: 5794422 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9406. Min Act: -0.1700
Data Index: 3950720 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9406. Min Act: -0.1700
Data Index: 3950719 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9406. Min Act: -0.1700
Data Index: 6885254 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9406. Min Act: -0.1700
Data Index: 4291509 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9094. Min Act: -0.1700
Data Index: 7649205 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9094. Min Act: -0.1700
Data Index: 7524119 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.9094. Min Act: -0.1700
Data Index: 4666868 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8781. Min Act: -0.1700
Data Index: 2790451 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8781. Min Act: -0.1700
Data Index: 2360081 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8469. Min Act: -0.1700
Data Index: 441631 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8469. Min Act: -0.1700
Data Index: 1879577 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8156. Min Act: -0.1700
Data Index: 40370 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8156. Min Act: -0.1700
Data Index: 3829844 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8781. Min Act: -0.1700
Data Index: 2338991 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8156. Min Act: -0.1700
Data Index: 6885255 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8156. Min Act: -0.1700
Data Index: 3069969 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9719. Min Range: -4.9719
Max Act: 4.8156. Min Act: -0.1700
Data Index: 3600411 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19