Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2184 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6627. Min Range: -7.6627
Max Act: 7.6627. Min Act: -0.1700
Data Index: 5303340 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6627. Min Range: -7.6627
Max Act: 7.5690. Min Act: -0.1700
Data Index: 5560296 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6627. Min Range: -7.6627
Max Act: 7.2252. Min Act: -0.1700
Data Index: 6878377 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6627. Min Range: -7.6627
Max Act: 7.1627. Min Act: -0.1700
Data Index: 1428832 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6627. Min Range: -7.6627
Max Act: 7.1002. Min Act: -0.1700
Data Index: 287354 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6627. Min Range: -7.6627
Max Act: 7.0065. Min Act: -0.1700
Data Index: 4413879 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6627. Min Range: -7.6627
Max Act: 7.0065. Min Act: -0.1700
Data Index: 8040572 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6627. Min Range: -7.6627
Max Act: 7.0377. Min Act: -0.1700
Data Index: 7307871 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6627. Min Range: -7.6627
Max Act: 7.0065. Min Act: -0.1700
Data Index: 7804879 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.9752. Min Act: -0.1700
Data Index: 7314791 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.9752. Min Act: -0.1700
Data Index: 828867 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.8815. Min Act: -0.1700
Data Index: 6625540 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 33719 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.8815. Min Act: -0.1700
Data Index: 4870704 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 351697 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 4623028 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 1288694 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 6788697 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 423582 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6627. Min Range: -7.6627
Max Act: 6.8190. Min Act: -0.1700
Data Index: 4336619 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19