Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0486. Min Range: -3.0486
Max Act: 3.0328. Min Act: -0.1700
Data Index: 1995737 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0486. Min Range: -3.0486
Max Act: 3.0171. Min Act: -0.1700
Data Index: 1300164 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0486. Min Range: -3.0486
Max Act: 3.0486. Min Act: -0.1700
Data Index: 4273948 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9854. Min Act: -0.1700
Data Index: 3134738 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9696. Min Act: -0.1700
Data Index: 5578056 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9696. Min Act: -0.1700
Data Index: 3228426 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9538. Min Act: -0.1700
Data Index: 6433815 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9538. Min Act: -0.1700
Data Index: 8774024 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9380. Min Act: -0.1700
Data Index: 1656521 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9221. Min Act: -0.1700
Data Index: 93085 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8904. Min Act: -0.1700
Data Index: 2659436 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9063. Min Act: -0.1700
Data Index: 8702006 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8746. Min Act: -0.1700
Data Index: 7016407 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8746. Min Act: -0.1700
Data Index: 1589843 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8746. Min Act: -0.1700
Data Index: 5084534 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8746. Min Act: -0.1700
Data Index: 7542385 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8746. Min Act: -0.1700
Data Index: 8387993 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8428. Min Act: -0.1700
Data Index: 2924686 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8428. Min Act: -0.1700
Data Index: 5159189 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8587. Min Act: -0.1700
Data Index: 810546 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19