Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5457 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.3891. Min Act: -0.1700
Data Index: 7964465 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.3891. Min Act: -0.1700
Data Index: 4266236 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.3578. Min Act: -0.1700
Data Index: 8471095 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.3578. Min Act: -0.1700
Data Index: 6418164 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.3266. Min Act: -0.1700
Data Index: 1517470 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.2953. Min Act: -0.1700
Data Index: 8828595 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.2641. Min Act: -0.1700
Data Index: 632177 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.2016. Min Act: -0.1700
Data Index: 7468017 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.2328. Min Act: -0.1700
Data Index: 4086334 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.1703. Min Act: -0.1700
Data Index: 4360159 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.1703. Min Act: -0.1700
Data Index: 7392223 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.1078. Min Act: -0.1700
Data Index: 146262 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.1391. Min Act: -0.1700
Data Index: 1587538 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.1078. Min Act: -0.1700
Data Index: 8316203 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.1391. Min Act: -0.1700
Data Index: 7438345 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.1078. Min Act: -0.1700
Data Index: 2039980 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.1078. Min Act: -0.1700
Data Index: 292847 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.0766. Min Act: -0.1700
Data Index: 926839 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.0766. Min Act: -0.1700
Data Index: 2705660 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3891. Min Range: -5.3891
Max Act: 5.0453. Min Act: -0.1700
Data Index: 816751 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19