Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1050 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.9639. Min Act: -0.1700
Data Index: 4993755 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.5889. Min Act: -0.1700
Data Index: 2365385 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.5264. Min Act: -0.1700
Data Index: 4837926 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.5264. Min Act: -0.1700
Data Index: 2794674 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.5264. Min Act: -0.1700
Data Index: 8425706 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.4951. Min Act: -0.1700
Data Index: 5233191 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.4639. Min Act: -0.1700
Data Index: 1884024 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.4326. Min Act: -0.1700
Data Index: 580898 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.4326. Min Act: -0.1700
Data Index: 2294401 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.4326. Min Act: -0.1700
Data Index: 4287987 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.4014. Min Act: -0.1700
Data Index: 3708163 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.4014. Min Act: -0.1700
Data Index: 8421589 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.4014. Min Act: -0.1700
Data Index: 1161698 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.4014. Min Act: -0.1700
Data Index: 44641 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.3701. Min Act: -0.1700
Data Index: 2898639 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.3701. Min Act: -0.1700
Data Index: 5624059 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.3701. Min Act: -0.1700
Data Index: 6477523 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.3389. Min Act: -0.1700
Data Index: 1528261 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.3076. Min Act: -0.1700
Data Index: 1474966 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9639. Min Range: -6.9639
Max Act: 6.3076. Min Act: -0.1700
Data Index: 3784847 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19