Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.8891. Min Act: -0.1700
Data Index: 2094198 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.7953. Min Act: -0.1700
Data Index: 6175144 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.6391. Min Act: -0.1700
Data Index: 6006946 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.6703. Min Act: -0.1700
Data Index: 1176961 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.5766. Min Act: -0.1700
Data Index: 6019253 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.4516. Min Act: -0.1700
Data Index: 7739653 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.3891. Min Act: -0.1700
Data Index: 7712121 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.3578. Min Act: -0.1700
Data Index: 4711349 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.3266. Min Act: -0.1700
Data Index: 6552435 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.2641. Min Act: -0.1700
Data Index: 824112 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.2641. Min Act: -0.1700
Data Index: 2663961 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.2016. Min Act: -0.1700
Data Index: 6415840 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 6666340 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.1078. Min Act: -0.1700
Data Index: 8593264 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.0766. Min Act: -0.1700
Data Index: 5457574 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.0766. Min Act: -0.1700
Data Index: 7770466 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.0453. Min Act: -0.1700
Data Index: 3183704 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.0453. Min Act: -0.1700
Data Index: 492603 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8891. Min Range: -6.8891
Max Act: 6.0141. Min Act: -0.1700
Data Index: 3385893 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8891. Min Range: -6.8891
Max Act: 5.9828. Min Act: -0.1700
Data Index: 8089800 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19