Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1916 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.8057. Min Act: -0.1700
Data Index: 215766 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.8370. Min Act: -0.1700
Data Index: 5125141 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.8057. Min Act: -0.1700
Data Index: 2952359 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.7745. Min Act: -0.1700
Data Index: 3622077 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.8057. Min Act: -0.1700
Data Index: 5290553 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6495. Min Act: -0.1700
Data Index: 7728688 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6807. Min Act: -0.1700
Data Index: 5851012 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6495. Min Act: -0.1700
Data Index: 1339805 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6807. Min Act: -0.1700
Data Index: 2609731 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6182. Min Act: -0.1700
Data Index: 6566210 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6495. Min Act: -0.1700
Data Index: 3972700 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6495. Min Act: -0.1699
Data Index: 6442767 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6495. Min Act: -0.1700
Data Index: 5927898 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6495. Min Act: -0.1700
Data Index: 402355 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6495. Min Act: -0.1700
Data Index: 7639770 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6182. Min Act: -0.1700
Data Index: 6234593 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6182. Min Act: -0.1699
Data Index: 5173015 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.6182. Min Act: -0.1700
Data Index: 6777761 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.5870. Min Act: -0.1697
Data Index: 3064654 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8370. Min Range: -6.8370
Max Act: 6.5870. Min Act: -0.1700
Data Index: 3131986 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19