Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3110 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.7348. Min Act: -0.1700
Data Index: 5108508 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.7035. Min Act: -0.1700
Data Index: 5867193 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.7035. Min Act: -0.1700
Data Index: 1756416 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.6410. Min Act: -0.1700
Data Index: 3822903 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5473. Min Act: -0.1700
Data Index: 6472971 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5785. Min Act: -0.1700
Data Index: 2839 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5473. Min Act: -0.1700
Data Index: 8539792 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5473. Min Act: -0.1700
Data Index: 2248248 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5473. Min Act: -0.1700
Data Index: 1540302 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5160. Min Act: -0.1700
Data Index: 3696928 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5160. Min Act: -0.1700
Data Index: 5207810 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5160. Min Act: -0.1700
Data Index: 7196108 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 6920524 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5160. Min Act: -0.1700
Data Index: 2851812 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5160. Min Act: -0.1700
Data Index: 4298311 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 7409267 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 2754182 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5160. Min Act: -0.1700
Data Index: 2804854 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 737468 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 683065 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19