Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2873 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1478. Min Range: -6.1478
Max Act: 6.1478. Min Act: -0.1700
Data Index: 1449576 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1478. Min Range: -6.1478
Max Act: 6.0540. Min Act: -0.1700
Data Index: 3334736 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9915. Min Act: -0.1700
Data Index: 6984232 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9603. Min Act: -0.1700
Data Index: 5724140 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9290. Min Act: -0.1700
Data Index: 4075774 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9603. Min Act: -0.1700
Data Index: 881706 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9603. Min Act: -0.1700
Data Index: 2106670 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9603. Min Act: -0.1700
Data Index: 6452159 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9603. Min Act: -0.1700
Data Index: 483355 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9290. Min Act: -0.1700
Data Index: 6498990 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9290. Min Act: -0.1699
Data Index: 1869589 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9603. Min Act: -0.1700
Data Index: 5957634 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.8978. Min Act: -0.1700
Data Index: 566837 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.9290. Min Act: -0.1700
Data Index: 7000071 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.8978. Min Act: -0.1700
Data Index: 8094736 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.8665. Min Act: -0.1700
Data Index: 1461117 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.8978. Min Act: -0.1700
Data Index: 7408091 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.8665. Min Act: -0.1700
Data Index: 1612415 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.8353. Min Act: -0.1700
Data Index: 3233613 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1478. Min Range: -6.1478
Max Act: 5.8665. Min Act: -0.1700
Data Index: 4557757 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19