Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 426 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.9815. Min Act: -0.1700
Data Index: 654520 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.8565. Min Act: -0.1700
Data Index: 4383707 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.7315. Min Act: -0.1700
Data Index: 7978767 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.6065. Min Act: -0.1700
Data Index: 2721536 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.5752. Min Act: -0.1700
Data Index: 269917 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.5752. Min Act: -0.1700
Data Index: 1506356 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.5440. Min Act: -0.1700
Data Index: 5648678 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.4502. Min Act: -0.1700
Data Index: 195329 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.4190. Min Act: -0.1700
Data Index: 4955534 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.4190. Min Act: -0.1700
Data Index: 5588874 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.3877. Min Act: -0.1700
Data Index: 4619499 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.3565. Min Act: -0.1700
Data Index: 548491 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.3565. Min Act: -0.1700
Data Index: 1438412 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.3877. Min Act: -0.1700
Data Index: 2715562 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.3565. Min Act: -0.1700
Data Index: 4564364 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.3252. Min Act: -0.1700
Data Index: 7381446 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.3252. Min Act: -0.1700
Data Index: 3728765 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.2940. Min Act: -0.1700
Data Index: 579338 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.2940. Min Act: -0.1700
Data Index: 1238847 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9815. Min Range: -5.9815
Max Act: 5.2940. Min Act: -0.1700
Data Index: 1837292 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19