Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3663 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.8641. Min Act: -0.1700
Data Index: 3584 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.8016. Min Act: -0.1700
Data Index: 3827298 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.6766. Min Act: -0.1700
Data Index: 3560341 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.6766. Min Act: -0.1700
Data Index: 6455252 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.4578. Min Act: -0.1700
Data Index: 903242 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.3641. Min Act: -0.1700
Data Index: 4945621 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.2391. Min Act: -0.1700
Data Index: 1592053 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.1766. Min Act: -0.1700
Data Index: 322323 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.2078. Min Act: -0.1700
Data Index: 5633676 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.2391. Min Act: -0.1700
Data Index: 126740 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.2078. Min Act: -0.1700
Data Index: 7062370 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.2391. Min Act: -0.1700
Data Index: 5604569 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.2078. Min Act: -0.1700
Data Index: 5536010 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.1766. Min Act: -0.1700
Data Index: 6664249 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.1453. Min Act: -0.1700
Data Index: 1838105 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.1453. Min Act: -0.1700
Data Index: 2004344 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.1453. Min Act: -0.1700
Data Index: 1292018 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.1453. Min Act: -0.1700
Data Index: 5393095 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.1141. Min Act: -0.1700
Data Index: 3958597 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8641. Min Range: -7.8641
Max Act: 7.1141. Min Act: -0.1700
Data Index: 2807380 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19