Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4359 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.8607. Min Act: -0.1700
Data Index: 166253 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.8294. Min Act: -0.1700
Data Index: 4781481 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7982. Min Act: -0.1700
Data Index: 7459032 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7669. Min Act: -0.1700
Data Index: 7933138 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7669. Min Act: -0.1700
Data Index: 4571891 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7669. Min Act: -0.1700
Data Index: 1359008 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7356. Min Act: -0.1700
Data Index: 5289522 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7669. Min Act: -0.1700
Data Index: 941019 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7356. Min Act: -0.1700
Data Index: 8801754 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7356. Min Act: -0.1700
Data Index: 1746790 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7043. Min Act: -0.1700
Data Index: 7614498 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7356. Min Act: -0.1700
Data Index: 278114 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7043. Min Act: -0.1700
Data Index: 5146871 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.6730. Min Act: -0.1700
Data Index: 6991 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.6730. Min Act: -0.1700
Data Index: 3020406 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.6418. Min Act: -0.1700
Data Index: 7312930 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.6730. Min Act: -0.1700
Data Index: 6532144 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.7043. Min Act: -0.1700
Data Index: 5956366 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.6418. Min Act: -0.1700
Data Index: 3283008 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8607. Min Range: -3.8607
Max Act: 3.6105. Min Act: -0.1700
Data Index: 6115002 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19