Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.2790. Min Act: -0.1700
Data Index: 5238335 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.2478. Min Act: -0.1700
Data Index: 4297092 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.1853. Min Act: -0.1700
Data Index: 7192989 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.1540. Min Act: -0.1700
Data Index: 4181204 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.0915. Min Act: -0.1693
Data Index: 1531482 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.0603. Min Act: -0.1700
Data Index: 5238338 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.0290. Min Act: -0.1696
Data Index: 7753488 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.0603. Min Act: -0.1700
Data Index: 3643072 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.0603. Min Act: -0.1700
Data Index: 6130606 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.0290. Min Act: -0.1698
Data Index: 8640234 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2790. Min Range: -6.2790
Max Act: 5.9978. Min Act: -0.1700
Data Index: 5161406 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2790. Min Range: -6.2790
Max Act: 5.9978. Min Act: -0.1700
Data Index: 1010173 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2790. Min Range: -6.2790
Max Act: 5.9978. Min Act: -0.1700
Data Index: 7849929 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2790. Min Range: -6.2790
Max Act: 6.0290. Min Act: -0.1700
Data Index: 7373866 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2790. Min Range: -6.2790
Max Act: 5.9665. Min Act: -0.1699
Data Index: 7880729 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2790. Min Range: -6.2790
Max Act: 5.9353. Min Act: -0.1700
Data Index: 4889156 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2790. Min Range: -6.2790
Max Act: 5.9353. Min Act: -0.1700
Data Index: 596017 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2790. Min Range: -6.2790
Max Act: 5.9665. Min Act: -0.1700
Data Index: 476645 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2790. Min Range: -6.2790
Max Act: 5.9665. Min Act: -0.1700
Data Index: 2630316 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2790. Min Range: -6.2790
Max Act: 5.9353. Min Act: -0.1700
Data Index: 2011984 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19