Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3699 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1271. Min Range: -6.1271
Max Act: 6.1271. Min Act: -0.1700
Data Index: 7903430 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9708. Min Act: -0.1700
Data Index: 3034864 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9708. Min Act: -0.1700
Data Index: 3473280 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9708. Min Act: -0.1700
Data Index: 7929237 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9708. Min Act: -0.1700
Data Index: 5803380 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9396. Min Act: -0.1700
Data Index: 1713460 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9396. Min Act: -0.1700
Data Index: 896912 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9396. Min Act: -0.1700
Data Index: 284950 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9708. Min Act: -0.1700
Data Index: 6400089 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9083. Min Act: -0.1700
Data Index: 6992235 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9083. Min Act: -0.1700
Data Index: 3410615 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9083. Min Act: -0.1700
Data Index: 8764188 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8771. Min Act: -0.1700
Data Index: 6888111 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8771. Min Act: -0.1700
Data Index: 6880832 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8771. Min Act: -0.1700
Data Index: 7054103 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8771. Min Act: -0.1700
Data Index: 5465882 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8771. Min Act: -0.1700
Data Index: 5363625 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8771. Min Act: -0.1700
Data Index: 4328845 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8771. Min Act: -0.1700
Data Index: 2085408 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8458. Min Act: -0.1700
Data Index: 1938642 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19