Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5783 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8979. Min Range: -7.8979
Max Act: 7.8979. Min Act: -0.1700
Data Index: 3431940 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8979. Min Range: -7.8979
Max Act: 7.8042. Min Act: -0.1700
Data Index: 6339319 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8979. Min Range: -7.8979
Max Act: 7.4604. Min Act: -0.1700
Data Index: 7499984 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8979. Min Range: -7.8979
Max Act: 7.3042. Min Act: -0.1700
Data Index: 7499986 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8979. Min Range: -7.8979
Max Act: 7.0542. Min Act: -0.1700
Data Index: 8648484 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8979. Min Range: -7.8979
Max Act: 7.0854. Min Act: -0.1700
Data Index: 3794058 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.9917. Min Act: -0.1700
Data Index: 6451693 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.8979. Min Act: -0.1700
Data Index: 3473715 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.9292. Min Act: -0.1700
Data Index: 4029703 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.8979. Min Act: -0.1700
Data Index: 4840802 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.8667. Min Act: -0.1700
Data Index: 583810 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.8667. Min Act: -0.1700
Data Index: 1656245 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.8354. Min Act: -0.1700
Data Index: 7399133 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.8667. Min Act: -0.1700
Data Index: 8245865 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.8354. Min Act: -0.1700
Data Index: 3473699 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.7417. Min Act: -0.1700
Data Index: 1090556 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.7417. Min Act: -0.1700
Data Index: 1949706 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.7417. Min Act: -0.1700
Data Index: 968706 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.7104. Min Act: -0.1700
Data Index: 2266066 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8979. Min Range: -7.8979
Max Act: 6.7104. Min Act: -0.1700
Data Index: 3301609 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19