Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4205 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1725. Min Range: -7.1725
Max Act: 7.1725. Min Act: -0.1700
Data Index: 6542120 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1725. Min Range: -7.1725
Max Act: 7.1100. Min Act: -0.1700
Data Index: 8733460 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1725. Min Range: -7.1725
Max Act: 7.0162. Min Act: -0.1700
Data Index: 7657032 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.7037. Min Act: -0.1700
Data Index: 6867754 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.6412. Min Act: -0.1700
Data Index: 610714 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.6412. Min Act: -0.1700
Data Index: 4791580 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.6100. Min Act: -0.1700
Data Index: 5332791 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.5787. Min Act: -0.1700
Data Index: 8556069 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.5787. Min Act: -0.1700
Data Index: 3164135 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.4850. Min Act: -0.1700
Data Index: 1051577 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.4537. Min Act: -0.1700
Data Index: 5497450 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.4537. Min Act: -0.1700
Data Index: 6791257 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.4225. Min Act: -0.1700
Data Index: 8302971 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.3912. Min Act: -0.1700
Data Index: 97359 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.3912. Min Act: -0.1700
Data Index: 3151320 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.3912. Min Act: -0.1700
Data Index: 7239713 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.3912. Min Act: -0.1700
Data Index: 2936099 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.3600. Min Act: -0.1700
Data Index: 7472949 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.3600. Min Act: -0.1700
Data Index: 7866462 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1725. Min Range: -7.1725
Max Act: 6.3600. Min Act: -0.1700
Data Index: 27750 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19