Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1955 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1060. Min Range: -8.1060
Max Act: 8.1060. Min Act: -0.1700
Data Index: 4608220 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1060. Min Range: -8.1060
Max Act: 8.1060. Min Act: -0.1700
Data Index: 8720064 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.9810. Min Act: -0.1700
Data Index: 3803943 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.9810. Min Act: -0.1700
Data Index: 1899083 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.9185. Min Act: -0.1700
Data Index: 5912918 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.8560. Min Act: -0.1700
Data Index: 1907147 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.9185. Min Act: -0.1700
Data Index: 1907151 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.9185. Min Act: -0.1700
Data Index: 8108775 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.9185. Min Act: -0.1700
Data Index: 3803946 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.8560. Min Act: -0.1700
Data Index: 7425859 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.8560. Min Act: -0.1700
Data Index: 4198340 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.7935. Min Act: -0.1700
Data Index: 5570221 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.7935. Min Act: -0.1700
Data Index: 3157414 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.7935. Min Act: -0.1700
Data Index: 7848838 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.7935. Min Act: -0.1700
Data Index: 248884 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.7935. Min Act: -0.1700
Data Index: 8282055 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.7935. Min Act: -0.1700
Data Index: 4553849 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.7935. Min Act: -0.1700
Data Index: 3803945 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.7935. Min Act: -0.1700
Data Index: 1412861 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1060. Min Range: -8.1060
Max Act: 7.7310. Min Act: -0.1700
Data Index: 5555269 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19