Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1630 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.9053. Min Act: -0.1700
Data Index: 1494948 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.8115. Min Act: -0.1700
Data Index: 3333573 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.6865. Min Act: -0.1700
Data Index: 4344014 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.6865. Min Act: -0.1700
Data Index: 1752814 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.6240. Min Act: -0.1700
Data Index: 4049155 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.5928. Min Act: -0.1700
Data Index: 6073162 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.4678. Min Act: -0.1700
Data Index: 8192527 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.3115. Min Act: -0.1700
Data Index: 3757358 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2803. Min Act: -0.1700
Data Index: 7394439 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1865. Min Act: -0.1700
Data Index: 420089 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.2490. Min Act: -0.1700
Data Index: 5818067 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1865. Min Act: -0.1700
Data Index: 7301993 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1865. Min Act: -0.1700
Data Index: 147511 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1553. Min Act: -0.1700
Data Index: 1472045 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1865. Min Act: -0.1700
Data Index: 8831955 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1553. Min Act: -0.1700
Data Index: 3713103 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.1240. Min Act: -0.1700
Data Index: 6514967 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.0928. Min Act: -0.1700
Data Index: 6196184 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.0928. Min Act: -0.1700
Data Index: 1736236 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9053. Min Range: -7.9053
Max Act: 7.0928. Min Act: -0.1700
Data Index: 7740899 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19