Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.2716. Min Act: -0.1700
Data Index: 3406584 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.2716. Min Act: -0.1700
Data Index: 3065105 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.2403. Min Act: -0.1698
Data Index: 1888094 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.2091. Min Act: -0.1700
Data Index: 1824802 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.2091. Min Act: -0.1700
Data Index: 2006975 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.2091. Min Act: -0.1700
Data Index: 1121599 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.1466. Min Act: -0.1700
Data Index: 1281238 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.1466. Min Act: -0.1700
Data Index: 2222937 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0841. Min Act: -0.1700
Data Index: 2267451 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0841. Min Act: -0.1700
Data Index: 7679089 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0841. Min Act: -0.1700
Data Index: 878830 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0841. Min Act: -0.1700
Data Index: 8155469 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0841. Min Act: -0.1700
Data Index: 1539943 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0528. Min Act: -0.1700
Data Index: 508902 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0528. Min Act: -0.1700
Data Index: 6526433 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0528. Min Act: -0.1700
Data Index: 2501443 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0528. Min Act: -0.1700
Data Index: 1520324 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0216. Min Act: -0.1700
Data Index: 8689806 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2716. Min Range: -5.2716
Max Act: 5.0216. Min Act: -0.1700
Data Index: 8496718 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2716. Min Range: -5.2716
Max Act: 4.9591. Min Act: -0.1700
Data Index: 5908116 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19