Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.8178. Min Act: -0.1700
Data Index: 1971284 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.8178. Min Act: -0.1700
Data Index: 1670288 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.7866. Min Act: -0.1700
Data Index: 3430433 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.7866. Min Act: -0.1700
Data Index: 8218551 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.7553. Min Act: -0.1700
Data Index: 3600441 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.7553. Min Act: -0.1700
Data Index: 5733915 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.7553. Min Act: -0.1700
Data Index: 7210387 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.7553. Min Act: -0.1700
Data Index: 8525268 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.7553. Min Act: -0.1700
Data Index: 7624603 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.7241. Min Act: -0.1700
Data Index: 6902841 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6928. Min Act: -0.1700
Data Index: 2339474 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6928. Min Act: -0.1700
Data Index: 2269398 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6928. Min Act: -0.1700
Data Index: 1790503 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6928. Min Act: -0.1700
Data Index: 7801998 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6928. Min Act: -0.1700
Data Index: 4448359 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6928. Min Act: -0.1700
Data Index: 3600444 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6616. Min Act: -0.1700
Data Index: 7230052 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6303. Min Act: -0.1700
Data Index: 7087663 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6303. Min Act: -0.1700
Data Index: 2170273 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8178. Min Range: -4.8178
Max Act: 4.6303. Min Act: -0.1700
Data Index: 2170279 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19