Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2697 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.4914. Min Act: -0.1700
Data Index: 7963173 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.4914. Min Act: -0.1700
Data Index: 2157576 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.4289. Min Act: -0.1700
Data Index: 6596500 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.4601. Min Act: -0.1700
Data Index: 5606571 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.3351. Min Act: -0.1700
Data Index: 178486 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.3351. Min Act: -0.1700
Data Index: 2445717 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.2101. Min Act: -0.1700
Data Index: 1350896 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.1476. Min Act: -0.1700
Data Index: 7582089 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.1476. Min Act: -0.1700
Data Index: 3910984 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.1164. Min Act: -0.1700
Data Index: 1353212 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.1164. Min Act: -0.1700
Data Index: 3278970 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.1476. Min Act: -0.1700
Data Index: 7676083 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.0851. Min Act: -0.1700
Data Index: 4405243 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.0851. Min Act: -0.1700
Data Index: 2264205 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.0539. Min Act: -0.1700
Data Index: 8710562 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4914. Min Range: -5.4914
Max Act: 5.0539. Min Act: -0.1700
Data Index: 6006913 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4914. Min Range: -5.4914
Max Act: 4.9914. Min Act: -0.1700
Data Index: 4619957 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4914. Min Range: -5.4914
Max Act: 4.9914. Min Act: -0.1700
Data Index: 6674110 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4914. Min Range: -5.4914
Max Act: 4.9914. Min Act: -0.1700
Data Index: 7450643 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4914. Min Range: -5.4914
Max Act: 4.9914. Min Act: -0.1700
Data Index: 3332013 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19