Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6204 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3233. Min Range: -8.3233
Max Act: 8.3233. Min Act: -0.1700
Data Index: 7301721 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3233. Min Range: -8.3233
Max Act: 8.3233. Min Act: -0.1700
Data Index: 698983 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3233. Min Range: -8.3233
Max Act: 8.1045. Min Act: -0.1700
Data Index: 2043893 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3233. Min Range: -8.3233
Max Act: 8.0420. Min Act: -0.1700
Data Index: 3988937 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3233. Min Range: -8.3233
Max Act: 8.0733. Min Act: -0.1700
Data Index: 7610614 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3233. Min Range: -8.3233
Max Act: 8.0733. Min Act: -0.1700
Data Index: 7953398 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3233. Min Range: -8.3233
Max Act: 8.0733. Min Act: -0.1700
Data Index: 7324673 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3233. Min Range: -8.3233
Max Act: 8.0420. Min Act: -0.1700
Data Index: 20433 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3233. Min Range: -8.3233
Max Act: 8.0108. Min Act: -0.1700
Data Index: 4663050 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.9170. Min Act: -0.1700
Data Index: 1429766 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.8545. Min Act: -0.1700
Data Index: 7301722 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.8233. Min Act: -0.1700
Data Index: 10711 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.7608. Min Act: -0.1700
Data Index: 6208800 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.7295. Min Act: -0.1700
Data Index: 7520121 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.7295. Min Act: -0.1700
Data Index: 7508888 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.6358. Min Act: -0.1700
Data Index: 337954 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.6358. Min Act: -0.1700
Data Index: 6018256 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.6045. Min Act: -0.1700
Data Index: 6822742 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.6045. Min Act: -0.1700
Data Index: 6013158 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3233. Min Range: -8.3233
Max Act: 7.5733. Min Act: -0.1700
Data Index: 4498079 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19