Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.3387. Min Act: -0.1700
Data Index: 3789376 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.2762. Min Act: -0.1700
Data Index: 4464261 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.3075. Min Act: -0.1700
Data Index: 8094582 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.2450. Min Act: -0.1700
Data Index: 5789910 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.2450. Min Act: -0.1700
Data Index: 5324223 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.2137. Min Act: -0.1700
Data Index: 4999349 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.2137. Min Act: -0.1700
Data Index: 7912044 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1825. Min Act: -0.1700
Data Index: 1552574 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1825. Min Act: -0.1700
Data Index: 3136811 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1825. Min Act: -0.1700
Data Index: 4230494 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1825. Min Act: -0.1700
Data Index: 2164546 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1512. Min Act: -0.1700
Data Index: 2213863 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1200. Min Act: -0.1700
Data Index: 708896 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1512. Min Act: -0.1700
Data Index: 6565118 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1512. Min Act: -0.1700
Data Index: 2587607 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1200. Min Act: -0.1700
Data Index: 930392 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1200. Min Act: -0.1700
Data Index: 3909933 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.1200. Min Act: -0.1700
Data Index: 1393404 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.0887. Min Act: -0.1700
Data Index: 1541203 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3387. Min Range: -6.3387
Max Act: 6.0887. Min Act: -0.1700
Data Index: 4226984 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19