Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.9417. Min Act: -0.1700
Data Index: 7373325 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.6917. Min Act: -0.1700
Data Index: 7610690 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.6917. Min Act: -0.1700
Data Index: 5431979 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.6292. Min Act: -0.1700
Data Index: 7043762 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.6292. Min Act: -0.1700
Data Index: 3954919 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.6292. Min Act: -0.1700
Data Index: 6810367 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.5042. Min Act: -0.1700
Data Index: 8046557 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.4417. Min Act: -0.1700
Data Index: 1781994 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.4417. Min Act: -0.1700
Data Index: 4249100 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.3792. Min Act: -0.1700
Data Index: 5390911 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.3167. Min Act: -0.1700
Data Index: 6155265 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.3167. Min Act: -0.1700
Data Index: 5017736 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.2542. Min Act: -0.1700
Data Index: 6588811 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.2542. Min Act: -0.1700
Data Index: 8780671 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.2542. Min Act: -0.1700
Data Index: 7159999 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.2542. Min Act: -0.1700
Data Index: 7255375 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.1292. Min Act: -0.1700
Data Index: 6815373 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.1917. Min Act: -0.1700
Data Index: 1409463 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.1917. Min Act: -0.1700
Data Index: 4799392 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9417. Min Range: -9.9417
Max Act: 9.1292. Min Act: -0.1700
Data Index: 4491679 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19