Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.9888. Min Act: -0.1700
Data Index: 86889 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.9263. Min Act: -0.1699
Data Index: 4914484 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.8951. Min Act: -0.1700
Data Index: 4677393 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.8326. Min Act: -0.1700
Data Index: 1506511 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.8326. Min Act: -0.1700
Data Index: 1425812 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.8326. Min Act: -0.1700
Data Index: 2337258 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.8013. Min Act: -0.1700
Data Index: 213481 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.7076. Min Act: -0.1700
Data Index: 2892312 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.7076. Min Act: -0.1700
Data Index: 86890 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.6763. Min Act: -0.1700
Data Index: 6663608 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.6451. Min Act: -0.1700
Data Index: 733250 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.6451. Min Act: -0.1700
Data Index: 590977 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.6138. Min Act: -0.1700
Data Index: 2481403 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.6451. Min Act: -0.1700
Data Index: 8519990 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.6138. Min Act: -0.1700
Data Index: 8323395 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.5513. Min Act: -0.1700
Data Index: 3828969 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.6138. Min Act: -0.1700
Data Index: 6687098 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.5826. Min Act: -0.1700
Data Index: 8786381 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.5826. Min Act: -0.1700
Data Index: 2443321 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9888. Min Range: -5.9888
Max Act: 5.5513. Min Act: -0.1700
Data Index: 4212282 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19