Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4583. Min Range: -9.4583
Max Act: 9.4583. Min Act: -0.1700
Data Index: 1774042 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.7083. Min Act: -0.1700
Data Index: 6854368 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.7083. Min Act: -0.1700
Data Index: 1816590 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.7083. Min Act: -0.1700
Data Index: 8542056 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.6458. Min Act: -0.1700
Data Index: 4547861 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.7083. Min Act: -0.1700
Data Index: 8690571 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.6458. Min Act: -0.1700
Data Index: 2289477 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.7083. Min Act: -0.1700
Data Index: 2606783 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.5833. Min Act: -0.1700
Data Index: 192543 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.6458. Min Act: -0.1700
Data Index: 2684837 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.6458. Min Act: -0.1700
Data Index: 8552808 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.5833. Min Act: -0.1700
Data Index: 2827888 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.6458. Min Act: -0.1700
Data Index: 5394327 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.5208. Min Act: -0.1700
Data Index: 3428461 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.5208. Min Act: -0.1700
Data Index: 2878627 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.6458. Min Act: -0.1700
Data Index: 845884 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.5833. Min Act: -0.1700
Data Index: 7411411 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.5833. Min Act: -0.1700
Data Index: 1816592 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.5208. Min Act: -0.1700
Data Index: 3659939 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4583. Min Range: -9.4583
Max Act: 8.5208. Min Act: -0.1700
Data Index: 6830444 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19