Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3887. Min Range: -8.3887
Max Act: 8.3887. Min Act: -0.1700
Data Index: 7318669 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3887. Min Range: -8.3887
Max Act: 8.1387. Min Act: -0.1700
Data Index: 3488163 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3887. Min Range: -8.3887
Max Act: 8.0762. Min Act: -0.1700
Data Index: 952948 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.9512. Min Act: -0.1700
Data Index: 7463159 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.7637. Min Act: -0.1700
Data Index: 5403813 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.7637. Min Act: -0.1700
Data Index: 3595278 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.7012. Min Act: -0.1700
Data Index: 3777831 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.6387. Min Act: -0.1700
Data Index: 3423805 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.5762. Min Act: -0.1700
Data Index: 2708869 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.6075. Min Act: -0.1700
Data Index: 2803629 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.5137. Min Act: -0.1700
Data Index: 6587244 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.5137. Min Act: -0.1700
Data Index: 4754099 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.4825. Min Act: -0.1700
Data Index: 6718703 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.4825. Min Act: -0.1700
Data Index: 7330205 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.4512. Min Act: -0.1700
Data Index: 1456206 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.4200. Min Act: -0.1700
Data Index: 4186855 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.3887. Min Act: -0.1700
Data Index: 4942888 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.3887. Min Act: -0.1700
Data Index: 968964 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.3575. Min Act: -0.1700
Data Index: 4628037 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3887. Min Range: -8.3887
Max Act: 7.2950. Min Act: -0.1700
Data Index: 6414902 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19