Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2582 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.8308. Min Act: -0.1700
Data Index: 8809288 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.6433. Min Act: -0.1700
Data Index: 2013505 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.4558. Min Act: -0.1700
Data Index: 1972199 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.4246. Min Act: -0.1700
Data Index: 7587934 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.3621. Min Act: -0.1700
Data Index: 6965703 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.3308. Min Act: -0.1700
Data Index: 8744948 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.1433. Min Act: -0.1700
Data Index: 2074941 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.2058. Min Act: -0.1700
Data Index: 6939887 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.0183. Min Act: -0.1700
Data Index: 3343690 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.0496. Min Act: -0.1700
Data Index: 5362831 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8308. Min Range: -6.8308
Max Act: 5.9246. Min Act: -0.1700
Data Index: 1574370 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8308. Min Range: -6.8308
Max Act: 6.0183. Min Act: -0.1700
Data Index: 3855052 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8308. Min Range: -6.8308
Max Act: 5.9558. Min Act: -0.1700
Data Index: 7462027 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8308. Min Range: -6.8308
Max Act: 5.9246. Min Act: -0.1700
Data Index: 4875270 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8308. Min Range: -6.8308
Max Act: 5.9246. Min Act: -0.1700
Data Index: 8234455 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8308. Min Range: -6.8308
Max Act: 5.9558. Min Act: -0.1700
Data Index: 5795070 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8308. Min Range: -6.8308
Max Act: 5.8933. Min Act: -0.1700
Data Index: 125489 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8308. Min Range: -6.8308
Max Act: 5.8621. Min Act: -0.1700
Data Index: 7533234 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8308. Min Range: -6.8308
Max Act: 5.7371. Min Act: -0.1700
Data Index: 1726879 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8308. Min Range: -6.8308
Max Act: 5.7683. Min Act: -0.1700
Data Index: 7513144 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19