Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.8375. Min Act: -0.1700
Data Index: 2412164 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.7125. Min Act: -0.1700
Data Index: 6757322 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.6812. Min Act: -0.1700
Data Index: 5452142 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.6500. Min Act: -0.1700
Data Index: 6899807 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.6500. Min Act: -0.1700
Data Index: 2605151 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.5875. Min Act: -0.1700
Data Index: 5980827 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.5562. Min Act: -0.1700
Data Index: 5475720 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.4937. Min Act: -0.1700
Data Index: 1778183 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.4625. Min Act: -0.1700
Data Index: 1778171 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.4625. Min Act: -0.1700
Data Index: 2538227 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.4312. Min Act: -0.1700
Data Index: 2284807 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.4312. Min Act: -0.1700
Data Index: 6696500 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.4312. Min Act: -0.1700
Data Index: 1778177 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.4000. Min Act: -0.1700
Data Index: 2434747 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.4000. Min Act: -0.1700
Data Index: 5980828 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.3687. Min Act: -0.1700
Data Index: 1778180 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.3687. Min Act: -0.1700
Data Index: 3142524 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.3375. Min Act: -0.1700
Data Index: 5901937 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.3687. Min Act: -0.1700
Data Index: 8784688 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8375. Min Range: -4.8375
Max Act: 4.4000. Min Act: -0.1700
Data Index: 4998940 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19