Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.9842. Min Act: -0.1700
Data Index: 8357848 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.8904. Min Act: -0.1700
Data Index: 8657293 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.8592. Min Act: -0.1700
Data Index: 635006 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.8279. Min Act: -0.1700
Data Index: 5229804 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.8279. Min Act: -0.1700
Data Index: 1044955 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7654. Min Act: -0.1700
Data Index: 2035876 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7967. Min Act: -0.1700
Data Index: 1156268 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7342. Min Act: -0.1700
Data Index: 5099465 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7654. Min Act: -0.1700
Data Index: 4041135 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7342. Min Act: -0.1700
Data Index: 2757369 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7654. Min Act: -0.1700
Data Index: 831282 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7654. Min Act: -0.1700
Data Index: 5801712 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7654. Min Act: -0.1700
Data Index: 3680863 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7342. Min Act: -0.1700
Data Index: 7589878 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7342. Min Act: -0.1700
Data Index: 4316271 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7029. Min Act: -0.1700
Data Index: 5652213 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.7029. Min Act: -0.1700
Data Index: 4768778 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.6717. Min Act: -0.1700
Data Index: 6122594 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.6717. Min Act: -0.1700
Data Index: 8232211 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9842. Min Range: -5.9842
Max Act: 5.6404. Min Act: -0.1700
Data Index: 3019552 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19