Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0681. Min Range: -4.0681
Max Act: 4.0681. Min Act: -0.1700
Data Index: 7137756 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0681. Min Range: -4.0681
Max Act: 4.0368. Min Act: -0.1700
Data Index: 3829784 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.9743. Min Act: -0.1700
Data Index: 5861492 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.9118. Min Act: -0.1700
Data Index: 3187246 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.9118. Min Act: -0.1700
Data Index: 5396318 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.9118. Min Act: -0.1700
Data Index: 7927 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.9430. Min Act: -0.1700
Data Index: 3105852 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.8805. Min Act: -0.1700
Data Index: 5740197 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.9118. Min Act: -0.1700
Data Index: 583712 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.9118. Min Act: -0.1700
Data Index: 1468029 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.9118. Min Act: -0.1700
Data Index: 2112663 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.9118. Min Act: -0.1700
Data Index: 2627281 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.8805. Min Act: -0.1700
Data Index: 6679559 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.8805. Min Act: -0.1700
Data Index: 583709 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.8805. Min Act: -0.1700
Data Index: 805066 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.8805. Min Act: -0.1700
Data Index: 1043330 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.8805. Min Act: -0.1700
Data Index: 2442180 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.8805. Min Act: -0.1700
Data Index: 982640 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.8805. Min Act: -0.1700
Data Index: 1595656 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0681. Min Range: -4.0681
Max Act: 3.8805. Min Act: -0.1700
Data Index: 1510598 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19