Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4210 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.9778. Min Act: -0.1700
Data Index: 1827885 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.8528. Min Act: -0.1700
Data Index: 3702612 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.8840. Min Act: -0.1700
Data Index: 2107305 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.7590. Min Act: -0.1700
Data Index: 5450496 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.7278. Min Act: -0.1700
Data Index: 6777947 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.6965. Min Act: -0.1700
Data Index: 291514 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.6653. Min Act: -0.1700
Data Index: 5162408 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.6340. Min Act: -0.1700
Data Index: 3361068 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.6028. Min Act: -0.1700
Data Index: 3715485 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.5715. Min Act: -0.1700
Data Index: 3033689 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.5403. Min Act: -0.1700
Data Index: 6364164 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.5090. Min Act: -0.1700
Data Index: 7822549 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.5403. Min Act: -0.1700
Data Index: 5908334 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.5090. Min Act: -0.1700
Data Index: 1948733 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.4778. Min Act: -0.1700
Data Index: 7494125 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.4778. Min Act: -0.1700
Data Index: 8465232 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.4465. Min Act: -0.1700
Data Index: 2876532 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.4465. Min Act: -0.1700
Data Index: 828489 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.4465. Min Act: -0.1700
Data Index: 5313299 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9778. Min Range: -4.9778
Max Act: 4.4153. Min Act: -0.1700
Data Index: 326145 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19