Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4125. Min Range: -7.4125
Max Act: 7.4125. Min Act: -0.1700
Data Index: 757256 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4125. Min Range: -7.4125
Max Act: 7.0687. Min Act: -0.1700
Data Index: 941195 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4125. Min Range: -7.4125
Max Act: 7.0375. Min Act: -0.1700
Data Index: 7584696 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.9750. Min Act: -0.1700
Data Index: 8683826 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.9437. Min Act: -0.1700
Data Index: 2824283 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.9437. Min Act: -0.1700
Data Index: 2331460 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.8812. Min Act: -0.1700
Data Index: 8228181 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.8812. Min Act: -0.1700
Data Index: 952386 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.8187. Min Act: -0.1700
Data Index: 694818 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.8187. Min Act: -0.1700
Data Index: 5151104 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.8187. Min Act: -0.1700
Data Index: 7143348 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.7875. Min Act: -0.1700
Data Index: 644995 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.7875. Min Act: -0.1700
Data Index: 54141 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.7562. Min Act: -0.1700
Data Index: 6869164 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.7562. Min Act: -0.1700
Data Index: 4358259 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.8187. Min Act: -0.1700
Data Index: 1788264 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.7250. Min Act: -0.1700
Data Index: 8433819 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.6937. Min Act: -0.1700
Data Index: 6938694 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.6312. Min Act: -0.1700
Data Index: 6260790 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4125. Min Range: -7.4125
Max Act: 6.6000. Min Act: -0.1700
Data Index: 5868408 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19