Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0495. Min Range: -6.0495
Max Act: 6.0183. Min Act: -0.1700
Data Index: 6765112 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0495. Min Range: -6.0495
Max Act: 6.0495. Min Act: -0.1700
Data Index: 497819 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.8933. Min Act: -0.1700
Data Index: 3399043 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.8620. Min Act: -0.1700
Data Index: 7649666 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.8620. Min Act: -0.1700
Data Index: 3792917 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.7995. Min Act: -0.1700
Data Index: 6386196 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.7058. Min Act: -0.1700
Data Index: 1476426 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.7370. Min Act: -0.1700
Data Index: 6668053 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6745. Min Act: -0.1700
Data Index: 1943052 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6433. Min Act: -0.1700
Data Index: 7177333 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6433. Min Act: -0.1700
Data Index: 3053278 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.7058. Min Act: -0.1700
Data Index: 7860694 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6433. Min Act: -0.1700
Data Index: 659543 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6433. Min Act: -0.1700
Data Index: 8560656 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6433. Min Act: -0.1700
Data Index: 4995375 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6433. Min Act: -0.1700
Data Index: 8759556 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6745. Min Act: -0.1700
Data Index: 8330325 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6433. Min Act: -0.1700
Data Index: 1743885 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6433. Min Act: -0.1700
Data Index: 1986446 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0495. Min Range: -6.0495
Max Act: 5.6433. Min Act: -0.1700
Data Index: 5423747 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19