Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.6913. Min Act: -0.1700
Data Index: 896386 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.5975. Min Act: -0.1700
Data Index: 4528920 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2850. Min Act: -0.1700
Data Index: 7523029 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.2538. Min Act: -0.1700
Data Index: 6547392 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6913. Min Range: -6.6913
Max Act: 6.0663. Min Act: -0.1700
Data Index: 8050730 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.9725. Min Act: -0.1700
Data Index: 4411768 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.9725. Min Act: -0.1700
Data Index: 4520427 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.9413. Min Act: -0.1700
Data Index: 5127025 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.9100. Min Act: -0.1700
Data Index: 170846 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.9100. Min Act: -0.1700
Data Index: 7539887 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.9100. Min Act: -0.1700
Data Index: 2157270 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.8475. Min Act: -0.1700
Data Index: 6775997 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.8163. Min Act: -0.1700
Data Index: 4721140 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.8475. Min Act: -0.1700
Data Index: 7733393 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.8163. Min Act: -0.1700
Data Index: 1641653 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.7850. Min Act: -0.1700
Data Index: 7978707 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.7538. Min Act: -0.1700
Data Index: 4214245 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.7538. Min Act: -0.1700
Data Index: 1531960 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.7538. Min Act: -0.1700
Data Index: 3480813 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6913. Min Range: -6.6913
Max Act: 5.7538. Min Act: -0.1700
Data Index: 3811411 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19