Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1375. Min Range: -6.1375
Max Act: 6.1375. Min Act: -0.1700
Data Index: 2897881 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.8875. Min Act: -0.1700
Data Index: 7430057 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.8875. Min Act: -0.1700
Data Index: 704221 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.8250. Min Act: -0.1700
Data Index: 5344385 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.7312. Min Act: -0.1700
Data Index: 122917 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.7312. Min Act: -0.1700
Data Index: 7517181 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.7312. Min Act: -0.1700
Data Index: 121193 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.7312. Min Act: -0.1700
Data Index: 3085510 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.6062. Min Act: -0.1700
Data Index: 779354 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.6375. Min Act: -0.1700
Data Index: 5425501 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.6687. Min Act: -0.1700
Data Index: 5438074 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.6062. Min Act: -0.1700
Data Index: 728285 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.6062. Min Act: -0.1700
Data Index: 644672 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.6062. Min Act: -0.1700
Data Index: 6640753 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.6062. Min Act: -0.1700
Data Index: 4263531 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.6062. Min Act: -0.1700
Data Index: 825420 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.6062. Min Act: -0.1700
Data Index: 4976987 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.5750. Min Act: -0.1700
Data Index: 128076 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.5750. Min Act: -0.1700
Data Index: 4957971 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1375. Min Range: -6.1375
Max Act: 5.5750. Min Act: -0.1700
Data Index: 4102825 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19