Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2509 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.7801. Min Act: -0.1700
Data Index: 519537 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.6551. Min Act: -0.1700
Data Index: 5301703 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.6863. Min Act: -0.1700
Data Index: 4090658 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.6238. Min Act: -0.1700
Data Index: 6801957 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4676. Min Act: -0.1700
Data Index: 6129307 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4676. Min Act: -0.1700
Data Index: 149726 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 1122060 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 3356760 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 5100595 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 54639 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 4268614 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4363. Min Act: -0.1700
Data Index: 6783192 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 7014842 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 8169516 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3738. Min Act: -0.1700
Data Index: 4067054 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3738. Min Act: -0.1700
Data Index: 4977134 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3426. Min Act: -0.1700
Data Index: 3202722 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 2422231 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3738. Min Act: -0.1700
Data Index: 7534999 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3426. Min Act: -0.1700
Data Index: 5106479 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19