Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.2200. Min Act: -0.1700
Data Index: 4482675 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.1888. Min Act: -0.1700
Data Index: 6513534 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.1888. Min Act: -0.1700
Data Index: 1865558 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.1888. Min Act: -0.1700
Data Index: 7424760 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.1263. Min Act: -0.1700
Data Index: 6238324 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0638. Min Act: -0.1700
Data Index: 8712384 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0638. Min Act: -0.1700
Data Index: 3174003 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0638. Min Act: -0.1700
Data Index: 1013679 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0325. Min Act: -0.1700
Data Index: 316791 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0325. Min Act: -0.1700
Data Index: 3171115 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0325. Min Act: -0.1700
Data Index: 4990255 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0325. Min Act: -0.1700
Data Index: 5063038 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0013. Min Act: -0.1700
Data Index: 7765508 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0013. Min Act: -0.1700
Data Index: 8107565 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2200. Min Range: -5.2200
Max Act: 5.0013. Min Act: -0.1700
Data Index: 1865552 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2200. Min Range: -5.2200
Max Act: 4.9700. Min Act: -0.1700
Data Index: 2515313 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2200. Min Range: -5.2200
Max Act: 4.9700. Min Act: -0.1700
Data Index: 3406979 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2200. Min Range: -5.2200
Max Act: 4.9700. Min Act: -0.1700
Data Index: 4840691 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2200. Min Range: -5.2200
Max Act: 4.9700. Min Act: -0.1700
Data Index: 2018034 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2200. Min Range: -5.2200
Max Act: 4.9700. Min Act: -0.1700
Data Index: 5428117 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19