Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3875 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.3578. Min Act: -0.1700
Data Index: 8335212 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.3578. Min Act: -0.1700
Data Index: 546649 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2953. Min Act: -0.1700
Data Index: 5505009 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2641. Min Act: -0.1700
Data Index: 8399356 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2328. Min Act: -0.1700
Data Index: 770897 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2328. Min Act: -0.1700
Data Index: 6124596 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2328. Min Act: -0.1700
Data Index: 1360993 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2016. Min Act: -0.1700
Data Index: 4843631 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1703. Min Act: -0.1700
Data Index: 2486587 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1703. Min Act: -0.1700
Data Index: 5926760 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 5994775 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 6046291 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 5955057 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 3093516 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1078. Min Act: -0.1700
Data Index: 8044728 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1078. Min Act: -0.1700
Data Index: 7104041 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1078. Min Act: -0.1700
Data Index: 8610478 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.0766. Min Act: -0.1700
Data Index: 5089345 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.0453. Min Act: -0.1700
Data Index: 5628928 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.0453. Min Act: -0.1700
Data Index: 6406946 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19