Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.3145. Min Act: -0.1700
Data Index: 5033960 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.3145. Min Act: -0.1700
Data Index: 5051392 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.2832. Min Act: -0.1700
Data Index: 1059105 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.1895. Min Act: -0.1700
Data Index: 4774033 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.1270. Min Act: -0.1700
Data Index: 210597 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0957. Min Act: -0.1700
Data Index: 4145822 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0957. Min Act: -0.1700
Data Index: 8211391 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0644. Min Act: -0.1700
Data Index: 4790544 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0332. Min Act: -0.1700
Data Index: 3596482 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0332. Min Act: -0.1700
Data Index: 435449 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0019. Min Act: -0.1700
Data Index: 350121 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0019. Min Act: -0.1700
Data Index: 730396 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3145. Min Range: -4.3145
Max Act: 3.9707. Min Act: -0.1700
Data Index: 5009366 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0019. Min Act: -0.1700
Data Index: 5588657 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0019. Min Act: -0.1700
Data Index: 8720323 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3145. Min Range: -4.3145
Max Act: 3.9707. Min Act: -0.1700
Data Index: 4520498 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3145. Min Range: -4.3145
Max Act: 3.9707. Min Act: -0.1700
Data Index: 6794952 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3145. Min Range: -4.3145
Max Act: 3.9707. Min Act: -0.1700
Data Index: 1585791 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3145. Min Range: -4.3145
Max Act: 4.0019. Min Act: -0.1700
Data Index: 1033707 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3145. Min Range: -4.3145
Max Act: 3.9394. Min Act: -0.1700
Data Index: 3614921 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19