Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5086 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.5783. Min Act: -0.1700
Data Index: 492921 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.4845. Min Act: -0.1700
Data Index: 7795993 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.4220. Min Act: -0.1700
Data Index: 2289652 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.4220. Min Act: -0.1700
Data Index: 1573367 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.3908. Min Act: -0.1700
Data Index: 3605142 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.2345. Min Act: -0.1700
Data Index: 8163864 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.1408. Min Act: -0.1700
Data Index: 2024428 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.1095. Min Act: -0.1700
Data Index: 844814 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.0470. Min Act: -0.1700
Data Index: 1618403 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.0783. Min Act: -0.1700
Data Index: 6891563 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5783. Min Range: -7.5783
Max Act: 7.0158. Min Act: -0.1700
Data Index: 4508449 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5783. Min Range: -7.5783
Max Act: 6.9533. Min Act: -0.1700
Data Index: 336640 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5783. Min Range: -7.5783
Max Act: 6.9533. Min Act: -0.1700
Data Index: 991109 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5783. Min Range: -7.5783
Max Act: 6.9533. Min Act: -0.1700
Data Index: 839762 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5783. Min Range: -7.5783
Max Act: 6.9533. Min Act: -0.1700
Data Index: 3041987 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5783. Min Range: -7.5783
Max Act: 6.8908. Min Act: -0.1700
Data Index: 579861 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5783. Min Range: -7.5783
Max Act: 6.8595. Min Act: -0.1700
Data Index: 3391756 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5783. Min Range: -7.5783
Max Act: 6.8283. Min Act: -0.1700
Data Index: 4810074 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5783. Min Range: -7.5783
Max Act: 6.7970. Min Act: -0.1700
Data Index: 4206443 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5783. Min Range: -7.5783
Max Act: 6.7970. Min Act: -0.1700
Data Index: 3748465 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19