Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1012 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.9630. Min Act: -0.1700
Data Index: 3293178 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.7130. Min Act: -0.1700
Data Index: 8238865 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.5255. Min Act: -0.1700
Data Index: 8230231 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.4005. Min Act: -0.1700
Data Index: 3205941 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.4005. Min Act: -0.1700
Data Index: 1228969 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.3380. Min Act: -0.1700
Data Index: 6104757 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.3380. Min Act: -0.1700
Data Index: 791976 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.2130. Min Act: -0.1700
Data Index: 318557 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.2130. Min Act: -0.1700
Data Index: 7804480 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.1505. Min Act: -0.1700
Data Index: 8340837 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.1505. Min Act: -0.1700
Data Index: 586859 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.1505. Min Act: -0.1700
Data Index: 681678 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.1505. Min Act: -0.1700
Data Index: 4713604 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.1505. Min Act: -0.1700
Data Index: 2025105 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.1505. Min Act: -0.1700
Data Index: 7544515 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.1505. Min Act: -0.1700
Data Index: 6391762 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.0880. Min Act: -0.1700
Data Index: 5162079 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.0880. Min Act: -0.1700
Data Index: 5213897 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.0880. Min Act: -0.1700
Data Index: 1607578 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9630. Min Range: -8.9630
Max Act: 8.0880. Min Act: -0.1700
Data Index: 4141020 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19