Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 60 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1895. Min Range: -5.1895
Max Act: 5.1895. Min Act: -0.1700
Data Index: 6991185 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1895. Min Range: -5.1895
Max Act: 5.0332. Min Act: -0.1700
Data Index: 5823690 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.9707. Min Act: -0.1700
Data Index: 3320939 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.9707. Min Act: -0.1700
Data Index: 6921210 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.9395. Min Act: -0.1700
Data Index: 377607 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.9707. Min Act: -0.1700
Data Index: 8372632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.9707. Min Act: -0.1700
Data Index: 4952438 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.9082. Min Act: -0.1700
Data Index: 1260960 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.9082. Min Act: -0.1700
Data Index: 2755342 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.9082. Min Act: -0.1700
Data Index: 1287022 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8770. Min Act: -0.1700
Data Index: 8210580 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8770. Min Act: -0.1700
Data Index: 2648616 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8770. Min Act: -0.1700
Data Index: 7244163 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8457. Min Act: -0.1700
Data Index: 6591958 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8457. Min Act: -0.1700
Data Index: 4256105 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8457. Min Act: -0.1700
Data Index: 1428211 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8457. Min Act: -0.1700
Data Index: 3100893 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8457. Min Act: -0.1700
Data Index: 5889932 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8770. Min Act: -0.1700
Data Index: 6984044 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1895. Min Range: -5.1895
Max Act: 4.8457. Min Act: -0.1700
Data Index: 1320325 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19