Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 596 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.2811. Min Act: -0.1700
Data Index: 7176534 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.2811. Min Act: -0.1700
Data Index: 4620885 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.2499. Min Act: -0.1700
Data Index: 8658889 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.1874. Min Act: -0.1700
Data Index: 7338356 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.2186. Min Act: -0.1700
Data Index: 6906109 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.1249. Min Act: -0.1700
Data Index: 1649461 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.1561. Min Act: -0.1700
Data Index: 4965039 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.1249. Min Act: -0.1700
Data Index: 1451686 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.1249. Min Act: -0.1700
Data Index: 7504592 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.0624. Min Act: -0.1700
Data Index: 1134818 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.0624. Min Act: -0.1700
Data Index: 4055678 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2811. Min Range: -7.2811
Max Act: 7.0311. Min Act: -0.1700
Data Index: 569055 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2811. Min Range: -7.2811
Max Act: 6.9999. Min Act: -0.1700
Data Index: 7675185 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2811. Min Range: -7.2811
Max Act: 6.9686. Min Act: -0.1700
Data Index: 4766762 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2811. Min Range: -7.2811
Max Act: 6.9686. Min Act: -0.1700
Data Index: 6898698 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2811. Min Range: -7.2811
Max Act: 6.9374. Min Act: -0.1700
Data Index: 7543576 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2811. Min Range: -7.2811
Max Act: 6.9374. Min Act: -0.1700
Data Index: 2061698 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2811. Min Range: -7.2811
Max Act: 6.9061. Min Act: -0.1700
Data Index: 4705017 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2811. Min Range: -7.2811
Max Act: 6.9061. Min Act: -0.1700
Data Index: 3061470 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2811. Min Range: -7.2811
Max Act: 6.9061. Min Act: -0.1700
Data Index: 6146795 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19