Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2651 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.7378. Min Act: -0.1700
Data Index: 6228709 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.6417. Min Act: -0.1700
Data Index: 5277920 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.6738. Min Act: -0.1700
Data Index: 956131 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.6417. Min Act: -0.1700
Data Index: 6479564 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.6417. Min Act: -0.1700
Data Index: 2032166 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.6417. Min Act: -0.1700
Data Index: 7016849 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.6096. Min Act: -0.1700
Data Index: 2587250 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.6096. Min Act: -0.1700
Data Index: 2915791 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.6096. Min Act: -0.1700
Data Index: 8601889 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.6096. Min Act: -0.1700
Data Index: 188542 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5774. Min Act: -0.1700
Data Index: 5277919 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5774. Min Act: -0.1700
Data Index: 6614995 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5451. Min Act: -0.1700
Data Index: 7350047 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5451. Min Act: -0.1698
Data Index: 8056437 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5451. Min Act: -0.1700
Data Index: 2914664 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5451. Min Act: -0.1700
Data Index: 5277921 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5451. Min Act: -0.1700
Data Index: 8366204 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5774. Min Act: -0.1700
Data Index: 3527620 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5451. Min Act: -0.1700
Data Index: 3619771 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7378. Min Range: -2.7378
Max Act: 2.5451. Min Act: -0.1700
Data Index: 3868763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19