Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0553. Min Range: -8.0553
Max Act: 8.0553. Min Act: -0.1700
Data Index: 7569236 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0553. Min Range: -8.0553
Max Act: 7.6803. Min Act: -0.1700
Data Index: 996525 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0553. Min Range: -8.0553
Max Act: 7.6178. Min Act: -0.1700
Data Index: 6386726 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0553. Min Range: -8.0553
Max Act: 7.3678. Min Act: -0.1700
Data Index: 6618765 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0553. Min Range: -8.0553
Max Act: 7.3053. Min Act: -0.1700
Data Index: 26450 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0553. Min Range: -8.0553
Max Act: 7.2428. Min Act: -0.1700
Data Index: 6292252 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0553. Min Range: -8.0553
Max Act: 7.2428. Min Act: -0.1700
Data Index: 2738619 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0553. Min Range: -8.0553
Max Act: 7.2428. Min Act: -0.1700
Data Index: 5665823 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0553. Min Range: -8.0553
Max Act: 7.1491. Min Act: -0.1700
Data Index: 165961 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0553. Min Range: -8.0553
Max Act: 7.0553. Min Act: -0.1700
Data Index: 6973049 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.9928. Min Act: -0.1700
Data Index: 3628097 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.9303. Min Act: -0.1700
Data Index: 4882418 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.8991. Min Act: -0.1700
Data Index: 6029404 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.8991. Min Act: -0.1700
Data Index: 5592096 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.8991. Min Act: -0.1700
Data Index: 6206236 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.8678. Min Act: -0.1700
Data Index: 3379701 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.8678. Min Act: -0.1700
Data Index: 1609908 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.8678. Min Act: -0.1700
Data Index: 369295 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.8678. Min Act: -0.1700
Data Index: 7964916 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0553. Min Range: -8.0553
Max Act: 6.8053. Min Act: -0.1700
Data Index: 673103 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19