Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 672 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.9726. Min Act: -0.1700
Data Index: 806383 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.8789. Min Act: -0.1700
Data Index: 4402900 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.8789. Min Act: -0.1700
Data Index: 5758751 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.8164. Min Act: -0.1700
Data Index: 8458531 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.7539. Min Act: -0.1700
Data Index: 5558817 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.6914. Min Act: -0.1700
Data Index: 2035777 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.6914. Min Act: -0.1700
Data Index: 5261344 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.6914. Min Act: -0.1700
Data Index: 3669780 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.6601. Min Act: -0.1700
Data Index: 2153724 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.5976. Min Act: -0.1700
Data Index: 8716705 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.5976. Min Act: -0.1700
Data Index: 5558830 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.5351. Min Act: -0.1700
Data Index: 6007578 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.5351. Min Act: -0.1700
Data Index: 721324 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.5351. Min Act: -0.1700
Data Index: 7993389 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.4726. Min Act: -0.1700
Data Index: 3959299 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.4726. Min Act: -0.1700
Data Index: 1336820 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.5039. Min Act: -0.1700
Data Index: 2793065 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.4414. Min Act: -0.1700
Data Index: 257462 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.4414. Min Act: -0.1700
Data Index: 3427249 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9726. Min Range: -6.9726
Max Act: 6.4414. Min Act: -0.1700
Data Index: 6129162 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19