Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0532. Min Range: -8.0532
Max Act: 8.0532. Min Act: -0.1700
Data Index: 5456900 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.9907. Min Act: -0.1700
Data Index: 4541219 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.9907. Min Act: -0.1700
Data Index: 7365793 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.8657. Min Act: -0.1700
Data Index: 1930107 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.7407. Min Act: -0.1700
Data Index: 7294636 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.7407. Min Act: -0.1700
Data Index: 4541841 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.7407. Min Act: -0.1700
Data Index: 1551919 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.6782. Min Act: -0.1700
Data Index: 2825326 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.6782. Min Act: -0.1700
Data Index: 8345787 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5844. Min Act: -0.1700
Data Index: 2501643 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.6157. Min Act: -0.1700
Data Index: 5981689 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5844. Min Act: -0.1700
Data Index: 8635638 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5532. Min Act: -0.1700
Data Index: 6043725 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5844. Min Act: -0.1700
Data Index: 8603484 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5844. Min Act: -0.1700
Data Index: 7103516 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5844. Min Act: -0.1700
Data Index: 5985145 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5532. Min Act: -0.1700
Data Index: 7720072 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5532. Min Act: -0.1700
Data Index: 4075873 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5219. Min Act: -0.1700
Data Index: 3596413 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0532. Min Range: -8.0532
Max Act: 7.5219. Min Act: -0.1700
Data Index: 6919942 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19