Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 188 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2709. Min Range: -4.2709
Max Act: 4.2709. Min Act: -0.1700
Data Index: 7129751 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2709. Min Range: -4.2709
Max Act: 4.0521. Min Act: -0.1700
Data Index: 5109666 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2709. Min Range: -4.2709
Max Act: 4.0208. Min Act: -0.1700
Data Index: 8716668 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9896. Min Act: -0.1700
Data Index: 628575 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2709. Min Range: -4.2709
Max Act: 4.0208. Min Act: -0.1700
Data Index: 1774042 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2709. Min Range: -4.2709
Max Act: 4.0834. Min Act: -0.1700
Data Index: 1370070 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2709. Min Range: -4.2709
Max Act: 4.0208. Min Act: -0.1700
Data Index: 3004109 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9583. Min Act: -0.1700
Data Index: 8300097 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2709. Min Range: -4.2709
Max Act: 4.0208. Min Act: -0.1700
Data Index: 8532798 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9896. Min Act: -0.1700
Data Index: 3777089 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9896. Min Act: -0.1700
Data Index: 7241529 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9896. Min Act: -0.1700
Data Index: 1244234 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9583. Min Act: -0.1700
Data Index: 5398664 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9583. Min Act: -0.1700
Data Index: 4132648 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9583. Min Act: -0.1700
Data Index: 3488450 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9271. Min Act: -0.1700
Data Index: 25425 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9271. Min Act: -0.1700
Data Index: 6188862 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9583. Min Act: -0.1700
Data Index: 1010915 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9271. Min Act: -0.1700
Data Index: 7091389 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2709. Min Range: -4.2709
Max Act: 3.9583. Min Act: -0.1700
Data Index: 2479122 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19