Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5530 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.5250. Min Act: -0.1700
Data Index: 4225620 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.3375. Min Act: -0.1700
Data Index: 2917367 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.2437. Min Act: -0.1700
Data Index: 5862936 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.2750. Min Act: -0.1700
Data Index: 799174 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.2437. Min Act: -0.1700
Data Index: 5739594 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1812. Min Act: -0.1700
Data Index: 7382211 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1500. Min Act: -0.1700
Data Index: 798048 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1500. Min Act: -0.1700
Data Index: 2835758 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1500. Min Act: -0.1700
Data Index: 36614 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1187. Min Act: -0.1700
Data Index: 2817928 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1187. Min Act: -0.1700
Data Index: 597665 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.0875. Min Act: -0.1700
Data Index: 6583494 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1187. Min Act: -0.1700
Data Index: 6344876 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1187. Min Act: -0.1700
Data Index: 1497870 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1187. Min Act: -0.1700
Data Index: 7712896 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.1187. Min Act: -0.1700
Data Index: 1497874 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.0875. Min Act: -0.1700
Data Index: 4667028 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.0875. Min Act: -0.1700
Data Index: 8009353 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.0875. Min Act: -0.1700
Data Index: 1573349 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5250. Min Range: -5.5250
Max Act: 5.0562. Min Act: -0.1700
Data Index: 5386194 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19