Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1844. Min Range: -7.1844
Max Act: 7.1844. Min Act: -0.1700
Data Index: 8153017 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1844. Min Range: -7.1844
Max Act: 7.1219. Min Act: -0.1700
Data Index: 7854364 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1844. Min Range: -7.1844
Max Act: 7.0594. Min Act: -0.1700
Data Index: 3218154 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.9656. Min Act: -0.1700
Data Index: 725783 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.9031. Min Act: -0.1700
Data Index: 6385201 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.8406. Min Act: -0.1700
Data Index: 6164183 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.7781. Min Act: -0.1700
Data Index: 7304534 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.7469. Min Act: -0.1700
Data Index: 2305116 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.7469. Min Act: -0.1700
Data Index: 3544908 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.7781. Min Act: -0.1700
Data Index: 4313436 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.7156. Min Act: -0.1700
Data Index: 3358162 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.6844. Min Act: -0.1700
Data Index: 7009244 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.6531. Min Act: -0.1700
Data Index: 5711846 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.6531. Min Act: -0.1700
Data Index: 4220462 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.6531. Min Act: -0.1700
Data Index: 5515671 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.5906. Min Act: -0.1700
Data Index: 3043424 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.6219. Min Act: -0.1700
Data Index: 601422 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.5906. Min Act: -0.1700
Data Index: 5993640 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.5594. Min Act: -0.1700
Data Index: 1743046 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1844. Min Range: -7.1844
Max Act: 6.5594. Min Act: -0.1700
Data Index: 2056120 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19