Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4985 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.3653. Min Act: -0.1700
Data Index: 5160348 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.2403. Min Act: -0.1700
Data Index: 2257863 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.1778. Min Act: -0.1700
Data Index: 911851 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.1778. Min Act: -0.1700
Data Index: 7057875 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0528. Min Act: -0.1700
Data Index: 1112361 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0840. Min Act: -0.1700
Data Index: 8134560 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0840. Min Act: -0.1700
Data Index: 6307591 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0528. Min Act: -0.1700
Data Index: 7298250 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0840. Min Act: -0.1700
Data Index: 777103 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0215. Min Act: -0.1700
Data Index: 6248104 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0215. Min Act: -0.1700
Data Index: 670844 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.9590. Min Act: -0.1700
Data Index: 65697 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.9903. Min Act: -0.1700
Data Index: 5291342 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.9590. Min Act: -0.1700
Data Index: 2650213 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.9590. Min Act: -0.1700
Data Index: 5768267 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.9903. Min Act: -0.1700
Data Index: 4010847 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.9590. Min Act: -0.1700
Data Index: 3022365 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.9278. Min Act: -0.1700
Data Index: 6044644 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8965. Min Act: -0.1700
Data Index: 4442149 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.9278. Min Act: -0.1700
Data Index: 6343580 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19