Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.6551. Min Act: -0.1700
Data Index: 4169869 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.6551. Min Act: -0.1700
Data Index: 2776438 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.3426. Min Act: -0.1700
Data Index: 5083413 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.4051. Min Act: -0.1700
Data Index: 1509599 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.3426. Min Act: -0.1700
Data Index: 5490217 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.2176. Min Act: -0.1700
Data Index: 2785697 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.1551. Min Act: -0.1700
Data Index: 6684750 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.1551. Min Act: -0.1700
Data Index: 930950 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.1551. Min Act: -0.1700
Data Index: 3912803 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6551. Min Range: -8.6551
Max Act: 8.1551. Min Act: -0.1700
Data Index: 3007923 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.9989. Min Act: -0.1700
Data Index: 6439972 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.9364. Min Act: -0.1700
Data Index: 3976916 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.9676. Min Act: -0.1700
Data Index: 1342801 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.9364. Min Act: -0.1700
Data Index: 4890974 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.9364. Min Act: -0.1700
Data Index: 3328288 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.9051. Min Act: -0.1700
Data Index: 4518346 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.8739. Min Act: -0.1700
Data Index: 377088 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.8739. Min Act: -0.1700
Data Index: 6226678 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.8426. Min Act: -0.1700
Data Index: 2425842 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6551. Min Range: -8.6551
Max Act: 7.8426. Min Act: -0.1700
Data Index: 1515482 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19