Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4909 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1376. Min Range: -4.1376
Max Act: 4.1376. Min Act: -0.1700
Data Index: 8639333 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1376. Min Range: -4.1376
Max Act: 4.0751. Min Act: -0.1700
Data Index: 7268607 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1376. Min Range: -4.1376
Max Act: 4.0751. Min Act: -0.1700
Data Index: 2469961 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1376. Min Range: -4.1376
Max Act: 4.0125. Min Act: -0.1700
Data Index: 8673713 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9813. Min Act: -0.1700
Data Index: 3936249 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9813. Min Act: -0.1700
Data Index: 5432474 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9813. Min Act: -0.1700
Data Index: 467813 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9500. Min Act: -0.1700
Data Index: 392239 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9500. Min Act: -0.1700
Data Index: 7108857 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9188. Min Act: -0.1700
Data Index: 4608307 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9500. Min Act: -0.1700
Data Index: 7160965 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9188. Min Act: -0.1700
Data Index: 7198797 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9188. Min Act: -0.1700
Data Index: 467812 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.9188. Min Act: -0.1700
Data Index: 1466785 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.8875. Min Act: -0.1700
Data Index: 2967452 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.8875. Min Act: -0.1700
Data Index: 4554800 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.8875. Min Act: -0.1700
Data Index: 8136617 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.8562. Min Act: -0.1700
Data Index: 4205801 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.8562. Min Act: -0.1700
Data Index: 7749229 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1376. Min Range: -4.1376
Max Act: 3.8562. Min Act: -0.1700
Data Index: 2340983 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19