Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.3578. Min Act: -0.1700
Data Index: 4183911 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.2641. Min Act: -0.1700
Data Index: 468597 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.2328. Min Act: -0.1700
Data Index: 975345 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.1703. Min Act: -0.1700
Data Index: 4596675 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.1703. Min Act: -0.1700
Data Index: 4418160 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.1703. Min Act: -0.1700
Data Index: 7908974 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.1078. Min Act: -0.1700
Data Index: 737322 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.0141. Min Act: -0.1700
Data Index: 3355852 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.8891. Min Act: -0.1700
Data Index: 1339400 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.8891. Min Act: -0.1700
Data Index: 3361226 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.8578. Min Act: -0.1700
Data Index: 947791 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.7641. Min Act: -0.1700
Data Index: 2872779 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.7641. Min Act: -0.1700
Data Index: 4194711 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.7016. Min Act: -0.1700
Data Index: 5874770 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.7016. Min Act: -0.1700
Data Index: 7679729 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.6391. Min Act: -0.1700
Data Index: 2633837 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.6391. Min Act: -0.1700
Data Index: 1825126 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.6391. Min Act: -0.1700
Data Index: 4107646 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.6391. Min Act: -0.1700
Data Index: 8348816 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.6078. Min Act: -0.1700
Data Index: 1673267 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19