Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.5790. Min Act: -0.1700
Data Index: 1722387 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.4853. Min Act: -0.1700
Data Index: 4565561 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.3915. Min Act: -0.1700
Data Index: 4497659 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.4540. Min Act: -0.1700
Data Index: 5554255 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.4540. Min Act: -0.1700
Data Index: 4130175 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.3603. Min Act: -0.1700
Data Index: 6522668 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.3290. Min Act: -0.1700
Data Index: 594090 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.3290. Min Act: -0.1700
Data Index: 2542637 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.2665. Min Act: -0.1700
Data Index: 1058378 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.2353. Min Act: -0.1700
Data Index: 667892 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.2353. Min Act: -0.1700
Data Index: 2464918 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.1728. Min Act: -0.1700
Data Index: 4294294 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.1415. Min Act: -0.1700
Data Index: 4413499 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.2040. Min Act: -0.1700
Data Index: 2232258 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.1728. Min Act: -0.1700
Data Index: 6238266 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.1728. Min Act: -0.1700
Data Index: 5109023 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.1415. Min Act: -0.1700
Data Index: 6474171 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.1415. Min Act: -0.1700
Data Index: 161268 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.1103. Min Act: -0.1700
Data Index: 6606375 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5790. Min Range: -6.5790
Max Act: 6.1103. Min Act: -0.1700
Data Index: 6605423 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19