Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4985 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.9524. Min Act: -0.1700
Data Index: 5170524 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.6712. Min Act: -0.1700
Data Index: 6231871 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.5149. Min Act: -0.1700
Data Index: 3205801 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.4524. Min Act: -0.1700
Data Index: 1171786 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.4212. Min Act: -0.1700
Data Index: 30881 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.4212. Min Act: -0.1700
Data Index: 3998713 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2962. Min Act: -0.1700
Data Index: 4245352 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.3274. Min Act: -0.1700
Data Index: 2665754 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2962. Min Act: -0.1700
Data Index: 5861731 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2962. Min Act: -0.1700
Data Index: 807877 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2649. Min Act: -0.1700
Data Index: 1539526 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2649. Min Act: -0.1700
Data Index: 223007 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2337. Min Act: -0.1700
Data Index: 2012950 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2337. Min Act: -0.1700
Data Index: 6835638 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2024. Min Act: -0.1700
Data Index: 5185862 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2024. Min Act: -0.1700
Data Index: 3487842 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2024. Min Act: -0.1700
Data Index: 3241337 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2024. Min Act: -0.1700
Data Index: 670194 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.2024. Min Act: -0.1700
Data Index: 3954120 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9524. Min Range: -7.9524
Max Act: 7.1399. Min Act: -0.1700
Data Index: 2187022 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19