Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1468. Min Range: -3.1468
Max Act: 3.1468. Min Act: -0.1700
Data Index: 4631223 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.9416. Min Act: -0.1700
Data Index: 5243102 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.9258. Min Act: -0.1700
Data Index: 4175283 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.9258. Min Act: -0.1700
Data Index: 637326 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.8941. Min Act: -0.1700
Data Index: 5878905 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.8782. Min Act: -0.1700
Data Index: 8355368 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.8623. Min Act: -0.1700
Data Index: 3550883 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.8305. Min Act: -0.1700
Data Index: 4815475 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.8305. Min Act: -0.1700
Data Index: 5403006 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7987. Min Act: -0.1700
Data Index: 174564 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7987. Min Act: -0.1700
Data Index: 5614452 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7987. Min Act: -0.1700
Data Index: 6151333 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7828. Min Act: -0.1700
Data Index: 4845890 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7828. Min Act: -0.1700
Data Index: 8319759 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7828. Min Act: -0.1700
Data Index: 4591718 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7668. Min Act: -0.1700
Data Index: 514704 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7828. Min Act: -0.1700
Data Index: 5195541 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7509. Min Act: -0.1700
Data Index: 6565466 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7509. Min Act: -0.1700
Data Index: 1719852 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1468. Min Range: -3.1468
Max Act: 2.7509. Min Act: -0.1700
Data Index: 4886894 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19