Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4010 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2853. Min Range: -9.2853
Max Act: 9.2853. Min Act: -0.1700
Data Index: 4065531 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2853. Min Range: -9.2853
Max Act: 9.0978. Min Act: -0.1700
Data Index: 8762173 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2853. Min Range: -9.2853
Max Act: 9.0978. Min Act: -0.1700
Data Index: 8235637 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2853. Min Range: -9.2853
Max Act: 9.0353. Min Act: -0.1700
Data Index: 8446837 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9728. Min Act: -0.1700
Data Index: 8235639 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9728. Min Act: -0.1700
Data Index: 2261116 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9728. Min Act: -0.1700
Data Index: 8235638 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9103. Min Act: -0.1700
Data Index: 7979414 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9728. Min Act: -0.1700
Data Index: 8446835 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9103. Min Act: -0.1700
Data Index: 40414 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9103. Min Act: -0.1700
Data Index: 5240471 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9103. Min Act: -0.1700
Data Index: 6604794 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9103. Min Act: -0.1700
Data Index: 8235644 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9103. Min Act: -0.1700
Data Index: 8235641 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.9103. Min Act: -0.1700
Data Index: 7632832 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.8478. Min Act: -0.1700
Data Index: 2856400 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.7853. Min Act: -0.1700
Data Index: 505889 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.8478. Min Act: -0.1700
Data Index: 4603300 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.8478. Min Act: -0.1700
Data Index: 4930987 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2853. Min Range: -9.2853
Max Act: 8.8478. Min Act: -0.1700
Data Index: 5294595 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19