Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1044 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2135. Min Range: -6.2135
Max Act: 6.2135. Min Act: -0.1700
Data Index: 8149578 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.9322. Min Act: -0.1700
Data Index: 6225884 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.9635. Min Act: -0.1700
Data Index: 7053606 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.9010. Min Act: -0.1700
Data Index: 8129645 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.8072. Min Act: -0.1700
Data Index: 8018121 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.8072. Min Act: -0.1700
Data Index: 2220617 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.7447. Min Act: -0.1700
Data Index: 2545965 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.7760. Min Act: -0.1700
Data Index: 638461 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.7760. Min Act: -0.1700
Data Index: 8246114 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.7447. Min Act: -0.1700
Data Index: 2562705 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.7760. Min Act: -0.1700
Data Index: 5840585 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.7447. Min Act: -0.1700
Data Index: 355053 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.7135. Min Act: -0.1700
Data Index: 8455232 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.7135. Min Act: -0.1700
Data Index: 3219339 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.6822. Min Act: -0.1700
Data Index: 2151292 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.6510. Min Act: -0.1700
Data Index: 1310318 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.6510. Min Act: -0.1700
Data Index: 4381737 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.6510. Min Act: -0.1700
Data Index: 2502283 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.6510. Min Act: -0.1700
Data Index: 3999771 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2135. Min Range: -6.2135
Max Act: 5.6510. Min Act: -0.1700
Data Index: 7860326 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19