Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5938 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0878. Min Range: -3.0878
Max Act: 3.0878. Min Act: -0.1700
Data Index: 3020579 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0878. Min Range: -3.0878
Max Act: 3.0720. Min Act: -0.1700
Data Index: 4014828 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0878. Min Range: -3.0878
Max Act: 3.0247. Min Act: -0.1700
Data Index: 7001404 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0878. Min Range: -3.0878
Max Act: 3.0247. Min Act: -0.1700
Data Index: 5732519 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0878. Min Range: -3.0878
Max Act: 3.0089. Min Act: -0.1700
Data Index: 1529934 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0878. Min Range: -3.0878
Max Act: 3.0089. Min Act: -0.1700
Data Index: 4250442 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0878. Min Range: -3.0878
Max Act: 3.0089. Min Act: -0.1700
Data Index: 5710954 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0878. Min Range: -3.0878
Max Act: 3.0089. Min Act: -0.1700
Data Index: 7397662 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9773. Min Act: -0.1700
Data Index: 5340736 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9931. Min Act: -0.1700
Data Index: 6817406 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9931. Min Act: -0.1700
Data Index: 80295 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9931. Min Act: -0.1700
Data Index: 5040459 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9931. Min Act: -0.1700
Data Index: 3950980 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9931. Min Act: -0.1700
Data Index: 4019680 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9615. Min Act: -0.1700
Data Index: 5081515 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9773. Min Act: -0.1700
Data Index: 2348818 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9773. Min Act: -0.1700
Data Index: 5732517 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9931. Min Act: -0.1700
Data Index: 688247 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9773. Min Act: -0.1700
Data Index: 2067451 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0878. Min Range: -3.0878
Max Act: 2.9615. Min Act: -0.1700
Data Index: 2573166 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19