Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.7141. Min Act: -0.1700
Data Index: 5869871 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.5266. Min Act: -0.1700
Data Index: 1955016 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.3391. Min Act: -0.1700
Data Index: 472370 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.3079. Min Act: -0.1700
Data Index: 7916859 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.2766. Min Act: -0.1700
Data Index: 2896017 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.2766. Min Act: -0.1700
Data Index: 1248790 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.2766. Min Act: -0.1700
Data Index: 7482523 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.1829. Min Act: -0.1700
Data Index: 1981807 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.1829. Min Act: -0.1700
Data Index: 369921 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.0891. Min Act: -0.1700
Data Index: 4969104 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.0579. Min Act: -0.1700
Data Index: 1602535 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.0579. Min Act: -0.1700
Data Index: 6827296 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.0266. Min Act: -0.1700
Data Index: 3997297 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.0266. Min Act: -0.1700
Data Index: 1829080 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.0266. Min Act: -0.1700
Data Index: 1935069 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7141. Min Range: -7.7141
Max Act: 6.9954. Min Act: -0.1700
Data Index: 6789079 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7141. Min Range: -7.7141
Max Act: 6.9954. Min Act: -0.1700
Data Index: 103829 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7141. Min Range: -7.7141
Max Act: 6.9954. Min Act: -0.1700
Data Index: 1105278 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7141. Min Range: -7.7141
Max Act: 7.0266. Min Act: -0.1700
Data Index: 1319110 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7141. Min Range: -7.7141
Max Act: 6.9641. Min Act: -0.1700
Data Index: 8556240 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19