Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.3578. Min Act: -0.1700
Data Index: 1182504 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2328. Min Act: -0.1700
Data Index: 680774 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2016. Min Act: -0.1700
Data Index: 6007163 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2016. Min Act: -0.1700
Data Index: 3377814 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2016. Min Act: -0.1700
Data Index: 4965902 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2328. Min Act: -0.1700
Data Index: 8744542 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1703. Min Act: -0.1700
Data Index: 5694371 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.2016. Min Act: -0.1700
Data Index: 6908540 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 3064382 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 7085612 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 918751 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 6175406 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 6210129 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 3192260 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1078. Min Act: -0.1700
Data Index: 3828928 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1078. Min Act: -0.1700
Data Index: 610701 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1078. Min Act: -0.1700
Data Index: 7528230 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.1391. Min Act: -0.1700
Data Index: 333161 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.0766. Min Act: -0.1700
Data Index: 1184533 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3578. Min Range: -5.3578
Max Act: 5.0766. Min Act: -0.1700
Data Index: 4985979 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19