Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5078 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2253. Min Range: -6.2253
Max Act: 6.2253. Min Act: -0.1700
Data Index: 2556251 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.8503. Min Act: -0.1700
Data Index: 4071531 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.7878. Min Act: -0.1700
Data Index: 4976819 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.6941. Min Act: -0.1700
Data Index: 2045043 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.6628. Min Act: -0.1700
Data Index: 4589357 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.6003. Min Act: -0.1700
Data Index: 7273717 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.6003. Min Act: -0.1700
Data Index: 6762728 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.5691. Min Act: -0.1700
Data Index: 4222706 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.5691. Min Act: -0.1700
Data Index: 5217758 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.5066. Min Act: -0.1700
Data Index: 8225822 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.4753. Min Act: -0.1700
Data Index: 3151184 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.4753. Min Act: -0.1700
Data Index: 8122384 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.4753. Min Act: -0.1700
Data Index: 8397595 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.4753. Min Act: -0.1700
Data Index: 6609932 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.4441. Min Act: -0.1700
Data Index: 4308587 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.4128. Min Act: -0.1700
Data Index: 6453285 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.3816. Min Act: -0.1700
Data Index: 4746285 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.3816. Min Act: -0.1700
Data Index: 794432 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.3816. Min Act: -0.1700
Data Index: 5691590 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2253. Min Range: -6.2253
Max Act: 5.3503. Min Act: -0.1700
Data Index: 7778558 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19