Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2613 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4673. Min Range: -8.4673
Max Act: 8.4673. Min Act: -0.1700
Data Index: 5724692 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.6548. Min Act: -0.1700
Data Index: 3426011 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.5298. Min Act: -0.1700
Data Index: 1601301 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.5298. Min Act: -0.1700
Data Index: 5554843 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.4673. Min Act: -0.1700
Data Index: 2823329 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.3736. Min Act: -0.1700
Data Index: 6131722 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.3423. Min Act: -0.1700
Data Index: 6878248 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.3423. Min Act: -0.1700
Data Index: 1677540 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.2173. Min Act: -0.1700
Data Index: 3137881 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.1861. Min Act: -0.1700
Data Index: 8818167 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.1548. Min Act: -0.1700
Data Index: 2906841 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.1548. Min Act: -0.1700
Data Index: 2701554 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.1236. Min Act: -0.1700
Data Index: 8160340 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.1236. Min Act: -0.1700
Data Index: 4768185 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.0923. Min Act: -0.1700
Data Index: 8649629 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.1236. Min Act: -0.1700
Data Index: 900702 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.0611. Min Act: -0.1700
Data Index: 4783717 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4673. Min Range: -8.4673
Max Act: 7.0611. Min Act: -0.1700
Data Index: 740729 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4673. Min Range: -8.4673
Max Act: 6.9986. Min Act: -0.1700
Data Index: 4830065 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4673. Min Range: -8.4673
Max Act: 6.9673. Min Act: -0.1700
Data Index: 141403 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19