Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.7792. Min Act: -0.1700
Data Index: 2330417 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.6542. Min Act: -0.1700
Data Index: 4754109 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.2167. Min Act: -0.1700
Data Index: 75678 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.2792. Min Act: -0.1700
Data Index: 7941893 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.2792. Min Act: -0.1700
Data Index: 1263417 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.1542. Min Act: -0.1700
Data Index: 293075 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.2792. Min Act: -0.1699
Data Index: 1949386 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.0917. Min Act: -0.1700
Data Index: 4110493 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.2167. Min Act: -0.1700
Data Index: 3339499 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.0292. Min Act: -0.1700
Data Index: 3935092 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.0292. Min Act: -0.1700
Data Index: 8291531 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7792. Min Range: -10.7792
Max Act: 10.0292. Min Act: -0.1700
Data Index: 5087679 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7792. Min Range: -10.7792
Max Act: 9.9667. Min Act: -0.1700
Data Index: 5367344 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7792. Min Range: -10.7792
Max Act: 9.9667. Min Act: -0.1700
Data Index: 803087 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7792. Min Range: -10.7792
Max Act: 9.9667. Min Act: -0.1674
Data Index: 3585446 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7792. Min Range: -10.7792
Max Act: 9.9667. Min Act: -0.1700
Data Index: 3801183 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7792. Min Range: -10.7792
Max Act: 9.9667. Min Act: -0.1700
Data Index: 1143912 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7792. Min Range: -10.7792
Max Act: 9.9667. Min Act: -0.1700
Data Index: 2315207 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7792. Min Range: -10.7792
Max Act: 9.9042. Min Act: -0.1697
Data Index: 914272 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7792. Min Range: -10.7792
Max Act: 9.8417. Min Act: -0.1700
Data Index: 5854907 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19