Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.7390. Min Act: -0.1700
Data Index: 6284854 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.6452. Min Act: -0.1700
Data Index: 3915745 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.3640. Min Act: -0.1700
Data Index: 495352 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.3327. Min Act: -0.1700
Data Index: 5200201 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.3327. Min Act: -0.1700
Data Index: 2230440 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.2702. Min Act: -0.1700
Data Index: 8669874 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.2077. Min Act: -0.1700
Data Index: 544294 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.2077. Min Act: -0.1700
Data Index: 7925424 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.1765. Min Act: -0.1700
Data Index: 2617097 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.1140. Min Act: -0.1700
Data Index: 6251922 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.1140. Min Act: -0.1700
Data Index: 294590 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.1140. Min Act: -0.1700
Data Index: 164740 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.0827. Min Act: -0.1700
Data Index: 6145747 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.0827. Min Act: -0.1700
Data Index: 8287785 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.0515. Min Act: -0.1700
Data Index: 6543929 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7390. Min Range: -7.7390
Max Act: 7.0515. Min Act: -0.1700
Data Index: 6034192 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7390. Min Range: -7.7390
Max Act: 6.9577. Min Act: -0.1700
Data Index: 5288479 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7390. Min Range: -7.7390
Max Act: 6.9577. Min Act: -0.1700
Data Index: 4030626 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7390. Min Range: -7.7390
Max Act: 6.9577. Min Act: -0.1700
Data Index: 2124337 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7390. Min Range: -7.7390
Max Act: 6.9577. Min Act: -0.1700
Data Index: 4775787 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19