Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1930. Min Range: -6.1930
Max Act: 6.1930. Min Act: -0.1700
Data Index: 3954933 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1930. Min Range: -6.1930
Max Act: 6.0993. Min Act: -0.1700
Data Index: 623559 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1930. Min Range: -6.1930
Max Act: 6.0368. Min Act: -0.1700
Data Index: 8591112 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.9743. Min Act: -0.1700
Data Index: 7948896 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.9430. Min Act: -0.1700
Data Index: 4959321 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.9430. Min Act: -0.1700
Data Index: 5960291 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.9430. Min Act: -0.1700
Data Index: 607035 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.8493. Min Act: -0.1700
Data Index: 7144907 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.8180. Min Act: -0.1700
Data Index: 2772690 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.7868. Min Act: -0.1700
Data Index: 562196 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.7868. Min Act: -0.1700
Data Index: 8499764 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.7555. Min Act: -0.1700
Data Index: 1421481 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.7555. Min Act: -0.1700
Data Index: 2511783 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.7555. Min Act: -0.1700
Data Index: 1470631 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.7555. Min Act: -0.1700
Data Index: 3458038 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.7243. Min Act: -0.1700
Data Index: 6931157 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.7243. Min Act: -0.1700
Data Index: 7455231 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.7243. Min Act: -0.1700
Data Index: 7457890 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.6930. Min Act: -0.1700
Data Index: 8130608 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1930. Min Range: -6.1930
Max Act: 5.6930. Min Act: -0.1700
Data Index: 4517164 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19