Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.5141. Min Act: -0.1700
Data Index: 524282 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.5141. Min Act: -0.1700
Data Index: 272977 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.3266. Min Act: -0.1700
Data Index: 5059995 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.2328. Min Act: -0.1700
Data Index: 1635688 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.2328. Min Act: -0.1700
Data Index: 140702 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.2016. Min Act: -0.1700
Data Index: 2392851 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.2328. Min Act: -0.1700
Data Index: 4292990 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.2016. Min Act: -0.1700
Data Index: 6379684 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.1391. Min Act: -0.1700
Data Index: 6678890 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.1391. Min Act: -0.1700
Data Index: 198737 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.1703. Min Act: -0.1700
Data Index: 3018584 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.1703. Min Act: -0.1700
Data Index: 3229801 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.1078. Min Act: -0.1700
Data Index: 3760801 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.1078. Min Act: -0.1700
Data Index: 8181824 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.1078. Min Act: -0.1700
Data Index: 8749130 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.1391. Min Act: -0.1700
Data Index: 4360263 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.0453. Min Act: -0.1700
Data Index: 2680423 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.0766. Min Act: -0.1700
Data Index: 1995912 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.0766. Min Act: -0.1700
Data Index: 248039 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5141. Min Range: -6.5141
Max Act: 6.0766. Min Act: -0.1700
Data Index: 3218546 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19