Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 381 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.7118. Min Act: -0.1700
Data Index: 1003041 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.7118. Min Act: -0.1700
Data Index: 1635578 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.7118. Min Act: -0.1700
Data Index: 7656834 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.7118. Min Act: -0.1700
Data Index: 3348553 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.7118. Min Act: -0.1700
Data Index: 2781690 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6806. Min Act: -0.1700
Data Index: 7120908 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6806. Min Act: -0.1700
Data Index: 7656835 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6806. Min Act: -0.1700
Data Index: 2013722 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6806. Min Act: -0.1700
Data Index: 693189 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6493. Min Act: -0.1700
Data Index: 5674856 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6493. Min Act: -0.1700
Data Index: 8322208 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6493. Min Act: -0.1700
Data Index: 1151694 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6493. Min Act: -0.1700
Data Index: 715003 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6493. Min Act: -0.1700
Data Index: 2338618 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6493. Min Act: -0.1700
Data Index: 8033128 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6493. Min Act: -0.1700
Data Index: 7728447 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6493. Min Act: -0.1700
Data Index: 495756 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6181. Min Act: -0.1700
Data Index: 3062787 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.5868. Min Act: -0.1700
Data Index: 2642451 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7118. Min Range: -4.7118
Max Act: 4.6181. Min Act: -0.1700
Data Index: 1300806 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19