Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 992 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.9558. Min Act: -0.1700
Data Index: 57460 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.8308. Min Act: -0.1700
Data Index: 1694880 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.7996. Min Act: -0.1700
Data Index: 182726 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.7683. Min Act: -0.1700
Data Index: 4844982 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.6433. Min Act: -0.1700
Data Index: 3773744 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.6433. Min Act: -0.1700
Data Index: 1715593 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.6120. Min Act: -0.1700
Data Index: 4018239 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.6120. Min Act: -0.1700
Data Index: 3872256 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.5808. Min Act: -0.1700
Data Index: 5204730 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.5183. Min Act: -0.1700
Data Index: 8391358 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.5183. Min Act: -0.1700
Data Index: 7869449 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.5183. Min Act: -0.1700
Data Index: 1162995 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.5183. Min Act: -0.1700
Data Index: 5290484 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.5495. Min Act: -0.1700
Data Index: 707416 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.5183. Min Act: -0.1700
Data Index: 1440770 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.4870. Min Act: -0.1700
Data Index: 5742658 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.4870. Min Act: -0.1700
Data Index: 3853905 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.4558. Min Act: -0.1700
Data Index: 4727322 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.5183. Min Act: -0.1700
Data Index: 5469742 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9558. Min Range: -4.9558
Max Act: 4.4870. Min Act: -0.1700
Data Index: 858628 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19