Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4063. Min Range: -6.4063
Max Act: 6.4063. Min Act: -0.1700
Data Index: 3364389 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4063. Min Range: -6.4063
Max Act: 6.3125. Min Act: -0.1700
Data Index: 2942322 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4063. Min Range: -6.4063
Max Act: 6.2500. Min Act: -0.1700
Data Index: 3006597 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4063. Min Range: -6.4063
Max Act: 6.1563. Min Act: -0.1700
Data Index: 4716740 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4063. Min Range: -6.4063
Max Act: 6.1875. Min Act: -0.1700
Data Index: 6864601 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.8750. Min Act: -0.1700
Data Index: 8155480 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.8750. Min Act: -0.1700
Data Index: 3961713 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.8125. Min Act: -0.1700
Data Index: 7007834 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.7813. Min Act: -0.1700
Data Index: 4593219 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.7813. Min Act: -0.1700
Data Index: 471858 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.7813. Min Act: -0.1700
Data Index: 6707172 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.7500. Min Act: -0.1700
Data Index: 8081722 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.7500. Min Act: -0.1700
Data Index: 68620 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.7188. Min Act: -0.1700
Data Index: 7161546 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.6875. Min Act: -0.1700
Data Index: 2550569 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.6563. Min Act: -0.1700
Data Index: 8360414 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.7188. Min Act: -0.1700
Data Index: 1147795 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.6875. Min Act: -0.1700
Data Index: 6096300 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.7188. Min Act: -0.1700
Data Index: 4182114 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4063. Min Range: -6.4063
Max Act: 5.7188. Min Act: -0.1700
Data Index: 1082490 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19