Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1638 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.5878. Min Act: -0.1700
Data Index: 2280169 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.5253. Min Act: -0.1700
Data Index: 7165250 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.4940. Min Act: -0.1700
Data Index: 8489793 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.3690. Min Act: -0.1700
Data Index: 5028828 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.3690. Min Act: -0.1700
Data Index: 6089788 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.3690. Min Act: -0.1700
Data Index: 3942504 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.3690. Min Act: -0.1700
Data Index: 5961228 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.3065. Min Act: -0.1700
Data Index: 4655662 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.3065. Min Act: -0.1700
Data Index: 7446682 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.2753. Min Act: -0.1700
Data Index: 190416 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.2753. Min Act: -0.1700
Data Index: 280824 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.2753. Min Act: -0.1700
Data Index: 2339479 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.2753. Min Act: -0.1700
Data Index: 7327997 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.2440. Min Act: -0.1700
Data Index: 7588427 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.2440. Min Act: -0.1700
Data Index: 190425 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.2128. Min Act: -0.1700
Data Index: 7244733 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.1815. Min Act: -0.1700
Data Index: 4725547 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.1815. Min Act: -0.1700
Data Index: 6160063 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.1503. Min Act: -0.1700
Data Index: 8622967 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5878. Min Range: -7.5878
Max Act: 7.1503. Min Act: -0.1700
Data Index: 8367193 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19